Academic literature on the topic 'Artificial Intelligence; Deep learning; Representation learning'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Artificial Intelligence; Deep learning; Representation learning.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Journal articles on the topic "Artificial Intelligence; Deep learning; Representation learning"
1
Renuka, Rajendra B., and Basavana Gowda Sharana. "Deep Learning Techniques for Complex Problems." Journal of Advances in Computational Intelligence Theory 2, no. 2 (2020): 1–5. https://doi.org/10.5281/zenodo.3946325.
Full textAbstract:
<em>Mimicking the brain is the most challenging task in the field of computer science since its origin. To achieve this many technologies were introduced namely Artificial intelligence, Machine learning, Neural networks, Deep learning. Among these Deep learning is the promising technique for the problems, which are not solved by neural network. In this paper we discussed the meaning of deep learning, it's scope, classification and Application. In addition to this we also discussed the future research using deep learning technique.</em>
2
Koohzadi, Maryam, Nasrollah Moghadam Charkari, and Foad Ghaderi. "Unsupervised representation learning based on the deep multi-view ensemble learning." Applied Intelligence 50, no. 2 (2019): 562–81. http://dx.doi.org/10.1007/s10489-019-01526-0.
Full text
3
Haghir Chehreghani, Morteza, and Mostafa Haghir Chehreghani. "Learning representations from dendrograms." Machine Learning 109, no. 9-10 (2020): 1779–802. http://dx.doi.org/10.1007/s10994-020-05895-3.
Full textAbstract:
Abstract We propose unsupervised representation learning and feature extraction from dendrograms. The commonly used Minimax distance measures correspond to building a dendrogram with single linkage criterion, with defining specific forms of a level function and a distance function over that. Therefore, we extend this method to arbitrary dendrograms. We develop a generalized framework wherein different distance measures and representations can be inferred from different types of dendrograms, level functions and distance functions. Via an appropriate embedding, we compute a vector-based representation of the inferred distances, in order to enable many numerical machine learning algorithms to employ such distances. Then, to address the model selection problem, we study the aggregation of different dendrogram-based distances respectively in solution space and in representation space in the spirit of deep representations. In the first approach, for example for the clustering problem, we build a graph with positive and negative edge weights according to the consistency of the clustering labels of different objects among different solutions, in the context of ensemble methods. Then, we use an efficient variant of correlation clustering to produce the final clusters. In the second approach, we investigate the combination of different distances and features sequentially in the spirit of multi-layered architectures to obtain the final features. Finally, we demonstrate the effectiveness of our approach via several numerical studies.
4
Chikwendu, Ijeoma Amuche, Xiaoling Zhang, Isaac Osei Agyemang, Isaac Adjei-Mensah, Ukwuoma Chiagoziem Chima, and Chukwuebuka Joseph Ejiyi. "A Comprehensive Survey on Deep Graph Representation Learning Methods." Journal of Artificial Intelligence Research 78 (October 25, 2023): 287–356. http://dx.doi.org/10.1613/jair.1.14768.
Full textAbstract:
There has been a lot of activity in graph representation learning in recent years. Graph representation learning aims to produce graph representation vectors to represent the structure and characteristics of huge graphs precisely. This is crucial since the effectiveness of the graph representation vectors will influence how well they perform in subsequent tasks like anomaly detection, connection prediction, and node classification. Recently, there has been an increase in the use of other deep-learning breakthroughs for data-based graph problems. Graph-based learning environments have a taxonomy of approaches, and this study reviews all their learning settings. The learning problem is theoretically and empirically explored. This study briefly introduces and summarizes the Graph Neural Architecture Search (G-NAS), outlines several Graph Neural Networks’ drawbacks, and suggests some strategies to mitigate these challenges. Lastly, the study discusses several potential future study avenues yet to be explored.
5
Jayanthila, Devi A., S. Aithal P., Mohan Radha, and Maurya Sudhanshu. "An Artificial Intelligence Deep Learning Model of Antiviral-HPV Protein Interaction Prediction." International Journal of Enhanced Research in Management & Computer Applications 11, no. 10 (2022): 32–41. https://doi.org/10.5281/zenodo.7538028.
Full textAbstract:
Many computer programmes can predict protein-protein interaction grounded with anamino acid sequence, although they tend to focus on species-specific interactions rather than cross-species ones. Homogeneous protein interaction prediction algorithms fail to find interactions between proteins from different species. In this research, we constructed an artificial intelligence deep learning model to encode the frequency of consecutive amino acids in a protein sequence. The deep learning model predicts human-viral protein interactions. The study used inartificial intelligence deep learning model and protein annotations to predict human-virus protein interactions. A simple but effective representation technique for predicting inter-species protein-protein interactions. The representation approach has several advantages, such as improving model performance, generating feature vectors, and applying the same representation to diverse protein types. The results of simulation shows that the proposed method achieves an accuracy of 98% than other methods.
6
de Bruin, Tim, Jens Kober, Karl Tuyls, and Robert Babuska. "Integrating State Representation Learning Into Deep Reinforcement Learning." IEEE Robotics and Automation Letters 3, no. 3 (2018): 1394–401. http://dx.doi.org/10.1109/lra.2018.2800101.
Full text
7
Ruiz-Garcia, Ariel, Jürgen Schmidhuber, Vasile Palade, Clive Cheong Took, and Danilo Mandic. "Deep neural network representation and Generative Adversarial Learning." Neural Networks 139 (July 2021): 199–200. http://dx.doi.org/10.1016/j.neunet.2021.03.009.
Full text
8
Sharma, Brahmansh. "Research Paper on Artificial Intelligence." INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 08, no. 07 (2024): 1–9. http://dx.doi.org/10.55041/ijsrem36678.
Full textAbstract:
Artificial Intelligence (AI) has emerged as a transformative force across various sectors, revolutionizing processes, enhancing efficiency, and redefining innovation. This research paper delves into the multifaceted landscape of AI, focusing on its applications, knowledge representation, and implications for innovation. The paper begins by exploring the diverse applications of AI across healthcare, gaming, finance, data security, social media, robotics, and e-commerce. In healthcare, AI aids in diagnosis and patient care, while in gaming, it enables strategic game play and enhances user experience. The finance sector leverages AI for automation, analytics, and algorithmic trading, improving decision-making and customer service. AI also plays a vital role in ensuring data security through advanced detection systems, manages vast social media data for enhanced user engagement, and drives innovation in robotics and e-commerce. Moving forward, the paper delves into the realm of expert systems and knowledge representation, elucidating the role of AI in simulating human expertise and modeling complex information structures. It discusses various aspects of knowledge representation, such as propositional knowledge representation, image retrieval, functional relationships between objects, and class representation formalism, highlighting their significance in developing intelligent systems. Furthermore, the paper examines the integration of AI in maintenance practices, both for tangible systems like engineering workshops and intangible products like data extraction wrappers. It underscores the importance of AI in optimizing operational efficiency, reducing downtime, and ensuring continuous data extraction. Lastly, the paper explores the concept of deep learning as a general- purpose invention, discussing its potential implications for innovation, management, institutions, and policy. It addresses key issues such as the management and organization of innovation, intellectual property rights, competition policy, and the cumulative knowledge production facilitated by deep learning. In conclusion, this research paper provides a comprehensive overview of AI's transformative potential, emphasizing the need for further research and analysis to fully comprehend its impact on society, economy, and innovation.
9
Rives, Alexander, Joshua Meier, Tom Sercu, et al. "Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences." Proceedings of the National Academy of Sciences 118, no. 15 (2021): e2016239118. http://dx.doi.org/10.1073/pnas.2016239118.
Full textAbstract:
In the field of artificial intelligence, a combination of scale in data and model capacity enabled by unsupervised learning has led to major advances in representation learning and statistical generation. In the life sciences, the anticipated growth of sequencing promises unprecedented data on natural sequence diversity. Protein language modeling at the scale of evolution is a logical step toward predictive and generative artificial intelligence for biology. To this end, we use unsupervised learning to train a deep contextual language model on 86 billion amino acids across 250 million protein sequences spanning evolutionary diversity. The resulting model contains information about biological properties in its representations. The representations are learned from sequence data alone. The learned representation space has a multiscale organization reflecting structure from the level of biochemical properties of amino acids to remote homology of proteins. Information about secondary and tertiary structure is encoded in the representations and can be identified by linear projections. Representation learning produces features that generalize across a range of applications, enabling state-of-the-art supervised prediction of mutational effect and secondary structure and improving state-of-the-art features for long-range contact prediction.
10
Tiwari, Tanya, Tanuj Tiwari, and Sanjay Tiwari. "How Artificial Intelligence, Machine Learning and Deep Learning are Radically Different?" International Journal of Advanced Research in Computer Science and Software Engineering 8, no. 2 (2018): 1. http://dx.doi.org/10.23956/ijarcsse.v8i2.569.
Full textAbstract:
There is a lot of confusion these days about Artificial Intelligence (AI), Machine Learning (ML) and Deep Learning (DL). A computer system able to perform tasks that normally require human intelligence, such as visual perception, speech recognition, decision-making, and translation between languages. Artificial Intelligence has made it possible. Deep learning is a subset of machine learning, and machine learning is a subset of AI, which is an umbrella term for any computer program that does something smart. In other words, all machine learning is AI, but not all AI is machine learning, and so forth. Machine Learning represents a key evolution in the fields of computer science, data analysis, software engineering, and artificial intelligence. Machine learning (ML)is a vibrant field of research, with a range of exciting areas for further development across different methods and applications. These areas include algorithmic interpretability, robustness, privacy, fairness, inference of causality, human-machine interaction, and security. The goal of ML is never to make “perfect” guesses, because ML deals in domains where there is no such thing. The goal is to make guesses that are good enough to be useful. Deep learning is a particular kind of machine learning that achieves great power and flexibility by learning to represent the world as nested hierarchy of concepts, with each concept defined in relation to simpler concepts, and more abstract representations computed in terms of less abstract ones. This paper gives an overview of artificial intelligence, machine learning & deep learning techniques and compare these techniques.
Dissertations / Theses on the topic "Artificial Intelligence; Deep learning; Representation learning"
1
Carvalho, Micael. "Deep representation spaces." Electronic Thesis or Diss., Sorbonne université, 2018. http://www.theses.fr/2018SORUS292.
Full textAbstract:
Ces dernières années, les techniques d’apprentissage profond ont fondamentalement transformé l'état de l'art de nombreuses applications de l'apprentissage automatique, devenant la nouvelle approche standard pour plusieurs d’entre elles. Les architectures provenant de ces techniques ont été utilisées pour l'apprentissage par transfert, ce qui a élargi la puissance des modèles profonds à des tâches qui ne disposaient pas de suffisamment de données pour les entraîner à partir de zéro. Le sujet d'étude de cette thèse couvre les espaces de représentation créés par les architectures profondes. Dans un premier temps, nous étudions les propriétés de leurs espaces, en prêtant un intérêt particulier à la redondance des dimensions et la précision numérique de leurs représentations. Nos résultats démontrent un fort degré de robustesse, pointant vers des schémas de compression simples et puissants. Ensuite, nous nous concentrons sur le l'affinement de ces représentations. Nous choisissons d'adopter un problème multi-tâches intermodal et de concevoir une fonction de coût capable de tirer parti des données de plusieurs modalités, tout en tenant compte des différentes tâches associées au même ensemble de données. Afin d'équilibrer correctement ces coûts, nous développons également un nouveau processus d'échantillonnage qui ne prend en compte que des exemples contribuant à la phase d'apprentissage, c'est-à-dire ceux ayant un coût positif. Enfin, nous testons notre approche sur un ensemble de données à grande échelle de recettes de cuisine et d'images associées. Notre méthode améliore de 5 fois l'état de l'art sur cette tâche, et nous montrons que l'aspect multitâche de notre approche favorise l'organisation sémantique de l'espace de représentation, lui permettant d'effectuer des sous-tâches jamais vues pendant l'entraînement, comme l'exclusion et la sélection d’ingrédients. Les résultats que nous présentons dans cette thèse ouvrent de nombreuses possibilités, y compris la compression de caractéristiques pour les applications distantes, l'apprentissage multi-modal et multitâche robuste et l'affinement de l'espace des caractéristiques. Pour l'application dans le contexte de la cuisine, beaucoup de nos résultats sont directement applicables dans une situation réelle, en particulier pour la détection d'allergènes, la recherche de recettes alternatives en raison de restrictions alimentaires et la planification de menus<br>In recent years, Deep Learning techniques have swept the state-of-the-art of many applications of Machine Learning, becoming the new standard approach for them. The architectures issued from these techniques have been used for transfer learning, which extended the power of deep models to tasks that did not have enough data to fully train them from scratch. This thesis' subject of study is the representation spaces created by deep architectures. First, we study properties inherent to them, with particular interest in dimensionality redundancy and precision of their features. Our findings reveal a strong degree of robustness, pointing the path to simple and powerful compression schemes. Then, we focus on refining these representations. We choose to adopt a cross-modal multi-task problem, and design a loss function capable of taking advantage of data coming from multiple modalities, while also taking into account different tasks associated to the same dataset. In order to correctly balance these losses, we also we develop a new sampling scheme that only takes into account examples contributing to the learning phase, i.e. those having a positive loss. Finally, we test our approach in a large-scale dataset of cooking recipes and associated pictures. Our method achieves a 5-fold improvement over the state-of-the-art, and we show that the multi-task aspect of our approach promotes a semantically meaningful organization of the representation space, allowing it to perform subtasks never seen during training, like ingredient exclusion and selection. The results we present in this thesis open many possibilities, including feature compression for remote applications, robust multi-modal and multi-task learning, and feature space refinement. For the cooking application, in particular, many of our findings are directly applicable in a real-world context, especially for the detection of allergens, finding alternative recipes due to dietary restrictions, and menu planning
2
Azizpour, Hossein. "Visual Representations and Models: From Latent SVM to Deep Learning." Doctoral thesis, KTH, Datorseende och robotik, CVAP, 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-192289.
Full textAbstract:
Two important components of a visual recognition system are representation and model. Both involves the selection and learning of the features that are indicative for recognition and discarding those features that are uninformative. This thesis, in its general form, proposes different techniques within the frameworks of two learning systems for representation and modeling. Namely, latent support vector machines (latent SVMs) and deep learning. First, we propose various approaches to group the positive samples into clusters of visually similar instances. Given a fixed representation, the sampled space of the positive distribution is usually structured. The proposed clustering techniques include a novel similarity measure based on exemplar learning, an approach for using additional annotation, and augmenting latent SVM to automatically find clusters whose members can be reliably distinguished from background class. In another effort, a strongly supervised DPM is suggested to study how these models can benefit from privileged information. The extra information comes in the form of semantic parts annotation (i.e. their presence and location). And they are used to constrain DPMs latent variables during or prior to the optimization of the latent SVM. Its effectiveness is demonstrated on the task of animal detection. Finally, we generalize the formulation of discriminative latent variable models, including DPMs, to incorporate new set of latent variables representing the structure or properties of negative samples. Thus, we term them as negative latent variables. We show this generalization affects state-of-the-art techniques and helps the visual recognition by explicitly searching for counter evidences of an object presence. Following the resurgence of deep networks, in the last works of this thesis we have focused on deep learning in order to produce a generic representation for visual recognition. A Convolutional Network (ConvNet) is trained on a largely annotated image classification dataset called ImageNet with $\sim1.3$ million images. Then, the activations at each layer of the trained ConvNet can be treated as the representation of an input image. We show that such a representation is surprisingly effective for various recognition tasks, making it clearly superior to all the handcrafted features previously used in visual recognition (such as HOG in our first works on DPM). We further investigate the ways that one can improve this representation for a task in mind. We propose various factors involving before or after the training of the representation which can improve the efficacy of the ConvNet representation. These factors are analyzed on 16 datasets from various subfields of visual recognition.<br><p>QC 20160908</p>
3
Panesar, Kulvinder. "Conversational artificial intelligence - demystifying statistical vs linguistic NLP solutions." Universitat Politécnica de Valéncia, 2020. http://hdl.handle.net/10454/18121.
Full textAbstract:
yes<br>This paper aims to demystify the hype and attention on chatbots and its association with conversational artificial intelligence. Both are slowly emerging as a real presence in our lives from the impressive technological developments in machine learning, deep learning and natural language understanding solutions. However, what is under the hood, and how far and to what extent can chatbots/conversational artificial intelligence solutions work – is our question. Natural language is the most easily understood knowledge representation for people, but certainly not the best for computers because of its inherent ambiguous, complex and dynamic nature. We will critique the knowledge representation of heavy statistical chatbot solutions against linguistics alternatives. In order to react intelligently to the user, natural language solutions must critically consider other factors such as context, memory, intelligent understanding, previous experience, and personalized knowledge of the user. We will delve into the spectrum of conversational interfaces and focus on a strong artificial intelligence concept. This is explored via a text based conversational software agents with a deep strategic role to hold a conversation and enable the mechanisms need to plan, and to decide what to do next, and manage the dialogue to achieve a goal. To demonstrate this, a deep linguistically aware and knowledge aware text based conversational agent (LING-CSA) presents a proof-of-concept of a non-statistical conversational AI solution.
4
Denize, Julien. "Self-supervised representation learning and applications to image and video analysis." Electronic Thesis or Diss., Normandie, 2023. http://www.theses.fr/2023NORMIR37.
Full textAbstract:
Dans cette thèse, nous développons des approches d'apprentissage auto-supervisé pour l'analyse d'images et de vidéos. L'apprentissage de représentation auto-supervisé permet de pré-entraîner les réseaux neuronaux à apprendre des concepts généraux sans annotations avant de les spécialiser plus rapidement à effectuer des tâches, et avec peu d'annotations. Nous présentons trois contributions à l'apprentissage auto-supervisé de représentations d'images et de vidéos. Premièrement, nous introduisons le paradigme théorique de l'apprentissage contrastif doux et sa mise en œuvre pratique appelée Estimation Contrastive de Similarité (SCE) qui relie l'apprentissage contrastif et relationnel pour la représentation d'images. Ensuite, SCE est étendue à l'apprentissage de représentation vidéo temporelle globale. Enfin, nous proposons COMEDIAN, un pipeline pour l'apprentissage de représentation vidéo locale-temporelle pour l'architecture transformer. Ces contributions ont conduit à des résultats de pointe sur de nombreux benchmarks et ont donné lieu à de multiples contributions académiques et techniques publiées<br>In this thesis, we develop approaches to perform self-supervised learning for image and video analysis. Self-supervised representation learning allows to pretrain neural networks to learn general concepts without labels before specializing in downstream tasks faster and with few annotations. We present three contributions to self-supervised image and video representation learning. First, we introduce the theoretical paradigm of soft contrastive learning and its practical implementation called Similarity Contrastive Estimation (SCE) connecting contrastive and relational learning for image representation. Second, SCE is extended to global temporal video representation learning. Lastly, we propose COMEDIAN a pipeline for local-temporal video representation learning for transformers. These contributions achieved state-of-the-art results on multiple benchmarks and led to several academic and technical published contributions
5
Tamaazousti, Youssef. "Vers l’universalité des représentations visuelle et multimodales." Thesis, Université Paris-Saclay (ComUE), 2018. http://www.theses.fr/2018SACLC038/document.
Full textAbstract:
En raison de ses enjeux sociétaux, économiques et culturels, l’intelligence artificielle (dénotée IA) est aujourd’hui un sujet d’actualité très populaire. L’un de ses principaux objectifs est de développer des systèmes qui facilitent la vie quotidienne de l’homme, par le biais d’applications telles que les robots domestiques, les robots industriels, les véhicules autonomes et bien plus encore. La montée en popularité de l’IA est fortement due à l’émergence d’outils basés sur des réseaux de neurones profonds qui permettent d’apprendre simultanément, la représentation des données (qui était traditionnellement conçue à la main), et la tâche à résoudre (qui était traditionnellement apprise à l’aide de modèles d’apprentissage automatique). Ceci résulte de la conjonction des avancées théoriques, de la capacité de calcul croissante ainsi que de la disponibilité de nombreuses données annotées. Un objectif de longue date de l’IA est de concevoir des machines inspirées des humains, capables de percevoir le monde, d’interagir avec les humains, et tout ceci de manière évolutive (c’est `a dire en améliorant constamment la capacité de perception du monde et d’interaction avec les humains). Bien que l’IA soit un domaine beaucoup plus vaste, nous nous intéressons dans cette thèse, uniquement à l’IA basée apprentissage (qui est l’une des plus performante, à ce jour). Celle-ci consiste `a l’apprentissage d’un modèle qui une fois appris résoud une certaine tâche, et est généralement composée de deux sous-modules, l’un représentant la donnée (nommé ”représentation”) et l’autre prenant des décisions (nommé ”résolution de tâche”). Nous catégorisons, dans cette thèse, les travaux autour de l’IA, dans les deux approches d’apprentissage suivantes : (i) Spécialisation : apprendre des représentations à partir de quelques tâches spécifiques dans le but de pouvoir effectuer des tâches très spécifiques (spécialisées dans un certain domaine) avec un très bon niveau de performance; ii) Universalité : apprendre des représentations à partir de plusieurs tâches générales dans le but d’accomplir autant de tâches que possible dansdifférents contextes. Alors que la spécialisation a été largement explorée par la communauté de l’apprentissage profond, seules quelques tentatives implicites ont été réalisée vers la seconde catégorie, à savoir, l’universalité. Ainsi, le but de cette thèse est d’aborder explicitement le problème de l’amélioration de l’universalité des représentations avec des méthodes d’apprentissage profond, pour les données d’image et de texte. [...]<br>Because of its key societal, economic and cultural stakes, Artificial Intelligence (AI) is a hot topic. One of its main goal, is to develop systems that facilitates the daily life of humans, with applications such as household robots, industrial robots, autonomous vehicle and much more. The rise of AI is highly due to the emergence of tools based on deep neural-networks which make it possible to simultaneously learn, the representation of the data (which were traditionally hand-crafted), and the task to solve (traditionally learned with statistical models). This resulted from the conjunction of theoretical advances, the growing computational capacity as well as the availability of many annotated data. A long standing goal of AI is to design machines inspired humans, capable of perceiving the world, interacting with humans, in an evolutionary way. We categorize, in this Thesis, the works around AI, in the two following learning-approaches: (i) Specialization: learn representations from few specific tasks with the goal to be able to carry out very specific tasks (specialized in a certain field) with a very good level of performance; (ii) Universality: learn representations from several general tasks with the goal to perform as many tasks as possible in different contexts. While specialization was extensively explored by the deep-learning community, only a few implicit attempts were made towards universality. Thus, the goal of this Thesis is to explicitly address the problem of improving universality with deep-learning methods, for image and text data. We have addressed this topic of universality in two different forms: through the implementation of methods to improve universality (“universalizing methods”); and through the establishment of a protocol to quantify its universality. Concerning universalizing methods, we proposed three technical contributions: (i) in a context of large semantic representations, we proposed a method to reduce redundancy between the detectors through, an adaptive thresholding and the relations between concepts; (ii) in the context of neural-network representations, we proposed an approach that increases the number of detectors without increasing the amount of annotated data; (iii) in a context of multimodal representations, we proposed a method to preserve the semantics of unimodal representations in multimodal ones. Regarding the quantification of universality, we proposed to evaluate universalizing methods in a Transferlearning scheme. Indeed, this technical scheme is relevant to assess the universal ability of representations. This also led us to propose a new framework as well as new quantitative evaluation criteria for universalizing methods
6
Cribier-Delande, Perrine. "Contexts and user modeling through disentangled representations learning." Electronic Thesis or Diss., Sorbonne université, 2021. http://www.theses.fr/2021SORUS407.
Full textAbstract:
Les récents succès, parfois très médiatisés, de l’apprentissage profond ont attiré beaucoup d'attention sur le domaine. Sa force réside dans sa capacité à apprendre des représentations d’objets complexes. Pour Renault, obtenir une représentation de conducteurs est un objectif à long terme, identifié depuis longtemps. Cela lui permettrait de mieux comprendre comment ses produits sont utilisés. Renault possède une grande connaissance de la voiture et des données qu’elle utilise et produit. Ces données sont presque entièrement contenues dans le CAN. Cependant, le CAN ne contient que le fonctionnement interne de la voiture (rien sur son environnement). De nombreux autres facteurs (tels que la météo, les autres usagers, l’état de la route...) peuvent affecter la conduite, il nous faut donc les démêler. Nous avons considéré l’utilisateur (ici le conducteur) comme un contexte comme les autres. En transférant des méthodes de démêlage utilisées en image, nous avons pu créer des modèles qui apprennent des représentations démêlées des contextes. Supervisés uniquement avec de la prédiction pendant l’entrainement, nos modèles sont capables de générer des données à partir des représentations de contextes apprises. Ils peuvent même représenter de nouveaux contextes, qui ne sont vus qu’après l'entrainement (durant l’inférence). Le transfert de ces modèles sur les données CAN a permis de confirmer que les informations sur les contextes de conduite (y compris l'identité des conducteurs) sont bien contenues dans le CAN<br>The recent, sometimes very publicised, successes have drawn a lot of attention to Deep Learning (DL). Many questions are asked about the limitations of these techniques. The great strength of DL is its ability to learn representations of complex objects. Renault, as a car manufacturer, has a vested interest in discovering how their cars are used. Learning representations of drivers is one of their long-term goals. Renault's strength partly lies in their knowledge of cars and the data they use and produce. This data is almost entirely contained in the Controller Area Network (CAN). However, the CAN data only contains the inner workings of a car and not its surroundings. As many factors exterior to the driver and the car (such as weather, other road users, road condition...) can affect driving, we must find a way to disentangle them.Seeing the user (or driver) as just another context allowed us to use context modelling approaches. By transferring disentanglement approaches used in computer vision, we were able to develop models that learn disentangled representations of contexts. We tested these models with a few public datasets of time series with clearly labelled contexts. Using only forecasting as supervision during training, our models are able to generate data only from the learned representations of contexts. They even learn to represent new contexts, only seen after training.We then transferred the developed models on CAN data and were able to confirm that information about driving contexts (including driver's identity) is indeed contained in the CAN
7
Kilinc, Ismail Ozsel. "Graph-based Latent Embedding, Annotation and Representation Learning in Neural Networks for Semi-supervised and Unsupervised Settings." Scholar Commons, 2017. https://scholarcommons.usf.edu/etd/7415.
Full textAbstract:
Machine learning has been immensely successful in supervised learning with outstanding examples in major industrial applications such as voice and image recognition. Following these developments, the most recent research has now begun to focus primarily on algorithms which can exploit very large sets of unlabeled examples to reduce the amount of manually labeled data required for existing models to perform well. In this dissertation, we propose graph-based latent embedding/annotation/representation learning techniques in neural networks tailored for semi-supervised and unsupervised learning problems. Specifically, we propose a novel regularization technique called Graph-based Activity Regularization (GAR) and a novel output layer modification called Auto-clustering Output Layer (ACOL) which can be used separately or collaboratively to develop scalable and efficient learning frameworks for semi-supervised and unsupervised settings.
First, singularly using the GAR technique, we develop a framework providing an effective and scalable graph-based solution for semi-supervised settings in which there exists a large number of observations but a small subset with ground-truth labels. The proposed approach is natural for the classification framework on neural networks as it requires no additional task calculating the reconstruction error (as in autoencoder based methods) or implementing zero-sum game mechanism (as in adversarial training based methods). We demonstrate that GAR effectively and accurately propagates the available labels to unlabeled examples. Our results show comparable performance with state-of-the-art generative approaches for this setting using an easier-to-train framework.
Second, we explore a different type of semi-supervised setting where a coarse level of labeling is available for all the observations but the model has to learn a fine, deeper level of latent annotations for each one. Problems in this setting are likely to be encountered in many domains such as text categorization, protein function prediction, image classification as well as in exploratory scientific studies such as medical and genomics research. We consider this setting as simultaneously performed supervised classification (per the available coarse labels) and unsupervised clustering (within each one of the coarse labels) and propose a novel framework combining GAR with ACOL, which enables the network to perform concurrent classification and clustering. We demonstrate how the coarse label supervision impacts performance and the classification task actually helps propagate useful clustering information between sub-classes. Comparative tests on the most popular image datasets rigorously demonstrate the effectiveness and competitiveness of the proposed approach.
The third and final setup builds on the prior framework to unlock fully unsupervised learning where we propose to substitute real, yet unavailable, parent- class information with pseudo class labels. In this novel unsupervised clustering approach the network can exploit hidden information indirectly introduced through a pseudo classification objective. We train an ACOL network through this pseudo supervision together with unsupervised objective based on GAR and ultimately obtain a k-means friendly latent representation. Furthermore, we demonstrate how the chosen transformation type impacts performance and helps propagate the latent information that is useful in revealing unknown clusters. Our results show state-of-the-art performance for unsupervised clustering tasks on MNIST, SVHN and USPS datasets with the highest accuracies reported to date in the literature.
8
El-Shaer, Mennat Allah. "An Experimental Evaluation of Probabilistic Deep Networks for Real-time Traffic Scene Representation using Graphical Processing Units." The Ohio State University, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=osu1546539166677894.
Full text
9
Marza, Pierre. "Learning spatial representations for single-task navigation and multi-task policies." Electronic Thesis or Diss., Lyon, INSA, 2024. http://www.theses.fr/2024ISAL0105.
Full textAbstract:
Agir de manière autonome dans notre monde 3D requiert un large éventail de compétences, parmi lesquelles se trouvent la perception du milieu environnant, sa représentation précise et suffisamment efficace pour garder une trace du passé, la prise de décisions et l’action en vue d’atteindre des objectifs. Les animaux, par exemple les humains, se distinguent par leur robustesse lorsqu’il s’agit d’agir dans le monde. En particulier, ils savent s’adapter efficacement à de nouveaux environnements, mais sont aussi capables de maîtriser rapidement de nombreuses tâches à partir de quelques exemples. Ce manuscrit étudiera comment les réseaux neuronaux artificiels peuvent être entrainés pour acquérir un sous-ensemble de ces capacités. Nous nous concentrerons tout d’abord sur l’entrainement d’agents neuronaux à la cartographie sémantique, à la fois à partir d’un signal de supervision augmenté et avec des représentations neuronales de scènes. Les agents neuronaux sont souvent entrainés par apprentissage par renforcement (RL) à partir d’un signal de récompense peu dense. Guider l’apprentissage des capacités de cartographie d’une scène en ajoutant au signal de supervision des tâches auxiliaires favorisant le raisonnement spatial aidera à naviguer plus efficacement. Au lieu de travailler sur le signal d’entrainement des agents neuronaux, nous verrons également comment l’incorporation de représentations neuronales spécifiques de la sémantique et de la géométrie à l’architecture de l’agent peut contribuer à améliorer les performances de navigation sémantique. Ensuite, nous étudierons la meilleure façon d’explorer un environnement 3D afin de construire des représentations neuronales de l’espace qui soient aussi satisfaisantes que possible sur la base de métriques pensées pour la robotique que nous proposerons. Enfin, nous passerons d’agents de navigation à des agents multi-tâches et nous verrons à quel point il est important d’adapter les caractéristiques visuelles extraites des observations de capteurs à chaque tâche à accomplir pour réaliser une variété de tâches, mais aussi pour s’adapter à de nouvelles tâches inconnues à partir de quelques démonstrations. Ce manuscrit abordera donc différentes questions : Comment représenter une scène 3D et garder une trace de l’expérience passée dans un environnement ? – Comment s’adapter de manière robuste à de nouveaux environnements, scénarios et potentiellement de nouvelles tâches ? – Comment entrainer des agents à des tâches séquentielles à horizon long ? – Comment maîtriser conjointement toutes les sous-compétences requises ? – Quelle est l’importance de la perception en robotique ?<br>Autonomously behaving in the 3D world requires a large set of skills, among which are perceiving the surrounding environment, representing it precisely and efficiently enough to keep track of the past, making decisions and acting to achieve specified goals. Animals, for instance humans, stand out by their robustness when it comes to acting in the world. In particular, they can efficiently generalize to new environments, but are also able to rapidly master many tasks of interest from a few examples. This manuscript will study how artificial neural networks can be trained to acquire a subset of these abilities. We will first focus on training neural agents to perform semantic mapping, both from augmented supervision signal and with proposed neural-based scene representations. Neural agents are often trained with Reinforcement Learning (RL) from a sparse reward signal. Guiding the learning of scene mapping abilities by augmenting the vanilla RL supervision signal with auxiliary spatial reasoning tasks will help navigating efficiently. Instead of modifying the training signal of neural agents, we will also see how incorporating specific neural-based representations of semantics and geometry within the architecture of the agent can help improve performance in goal-driven navigation. Then, we will study how to best explore a 3D environment in order to build neural representations of space that are as satisfying as possible based on robotic-oriented metrics we will propose. Finally, we will move from navigation-only to multi-task agents, and see how important it is to tailor visual features from sensor observations to the task at hand to perform a wide variety of tasks, but also to adapt to new unknown tasks from a few demonstrations. This manuscript will thus address different important questions such as: How to represent a 3D scene and keep track of previous experience in an environment? – How to robustly adapt to new environments, scenarios, and potentially new tasks? – How to train agents on long-horizon sequential tasks? – How to jointly master all required sub-skills? – What is the importance of perception in robotics?
10
Terreau, Enzo. "Apprentissage de représentations d'auteurs et d'autrices à partir de modèles de langue pour l'analyse des dynamiques d'écriture." Electronic Thesis or Diss., Lyon 2, 2024. http://www.theses.fr/2024LYO20001.
Full textAbstract:
La démocratisation récente et massive des outils numériques a donné à tous le moyen de produire de l'information et de la partager sur le web, que ce soit à travers des blogs, des réseaux sociaux, des plateformes de partage, ... La croissance exponentielle de cette masse d'information disponible, en grande partie textuelle, nécessite le développement de modèles de traitement automatique du langage naturel (TAL), afin de la représenter mathématiquement pour ensuite la classer, la trier ou la recommander. C'est l'apprentissage de représentation. Il vise à construire un espace de faible dimension où les distances entre les objets projetées (mots, textes) reflètent les distances constatées dans le monde réel, qu'elles soient sémantique, stylistique, ...La multiplication des données disponibles, combinée à l'explosion des moyens de calculs et l'essor de l'apprentissage profond à permis de créer des modèles de langue extrêmement performant pour le plongement des mots et des documents. Ils assimilent des notions sémantiques et de langue complexes, en restant accessibles à tous et facilement spécialisables sur des tâches ou des corpus plus spécifiques. Il est possible de les utiliser pour construire des plongements d'auteurices. Seulement il est difficile de savoir sur quels aspects un modèle va se focaliser pour les rapprocher ou les éloigner. Dans un cadre littéraire, il serait préférable que les similarités se rapportent principalement au style écrit. Plusieurs problèmes se posent alors. La définition du style littéraire est floue, il est difficile d'évaluer l'écart stylistique entre deux textes et donc entre leurs plongements. En linguistique computationnelle, les approches visant à le caractériser sont principalement statistiques, s'appuyant sur des marqueurs du langage. Fort de ces constats, notre première contribution propose une méthode d'évaluation de la capacité des modèles de langue à appréhender le style écrit. Nous aurons au préalable détaillé comment le texte est représenté en apprentissage automatique puis en apprentissage profond, au niveau du mot, du document puis des auteurices. Nous aurons aussi présenté le traitement de la notion de style littéraire en TAL, base de notre méthode. Le transfert de connaissances entre les boîtes noires que sont les grands modèles de langue et ces méthodes issues de la linguistique n'en demeure pas moins complexe. Notre seconde contribution vise à réconcilier ces approches via un modèle d'apprentissage de représentations d'auteurices se focalisant sur le style, VADES (Variational Author and Document Embedding with Style). Nous nous comparons aux méthodes existantes et analysons leurs limites dans cette optique-là. Enfin, nous nous intéressons à l'apprentissage de plongements dynamiques d'auteurices et de documents. En effet, l'information temporelle est cruciale et permet une représentation plus fine des dynamiques d'écriture. Après une présentation de l'état de l'art, nous détaillons notre dernière contribution, B²ADE (Brownian Bridge for Author and Document Embedding), modélisant les auteurices comme des trajectoires. Nous finissons en décrivant plusieurs axes d'améliorations de nos méthodes ainsi que quelques problématiques pour de futurs travaux<br>The recent and massive democratization of digital tools has empowered individuals to generate and share information on the web through various means such as blogs, social networks, sharing platforms, and more. The exponential growth of available information, mostly textual data, requires the development of Natural Language Processing (NLP) models to mathematically represent it and subsequently classify, sort, or recommend it. This is the essence of representation learning. It aims to construct a low-dimensional space where the distances between projected objects (words, texts) reflect real-world distances, whether semantic, stylistic, and so on.The proliferation of available data, coupled with the rise in computing power and deep learning, has led to the creation of highly effective language models for word and document embeddings. These models incorporate complex semantic and linguistic concepts while remaining accessible to everyone and easily adaptable to specific tasks or corpora. One can use them to create author embeddings. However, it is challenging to determine the aspects on which a model will focus to bring authors closer or move them apart. In a literary context, it is preferable for similarities to primarily relate to writing style, which raises several issues. The definition of literary style is vague, assessing the stylistic difference between two texts and their embeddings is complex. In computational linguistics, approaches aiming to characterize it are mainly statistical, relying on language markers. In light of this, our first contribution is a framework to evaluate the ability of language models to grasp writing style. We will have previously elaborated on text embedding models in machine learning and deep learning, at the word, document, and author levels. We will also have presented the treatment of the notion of literary style in Natural Language Processing, which forms the basis of our method. Transferring knowledge between black-box large language models and these methods derived from linguistics remains a complex task. Our second contribution aims to reconcile these approaches through a representation learning model focusing on style, VADES (Variational Author and Document Embedding with Style). We compare our model to state-of-the-art ones and analyze their limitations in this context.Finally, we delve into dynamic author and document embeddings. Temporal information is crucial, allowing for a more fine-grained representation of writing dynamics. After presenting the state of the art, we elaborate on our last contribution, B²ADE (Brownian Bridge Author and Document Embedding), which models authors as trajectories. We conclude by outlining several leads for improving our methods and highlighting potential research directions for the future
Books on the topic "Artificial Intelligence; Deep learning; Representation learning"
1
Goar, Vishal, Aditi Sharma, Jungpil Shin, and M. Firoz Mridha, eds. Deep Learning and Visual Artificial Intelligence. Springer Nature Singapore, 2024. http://dx.doi.org/10.1007/978-981-97-4533-3.
Full text
2
Troiano, Luigi, Alfredo Vaccaro, Roberto Tagliaferri, et al., eds. Advances in Deep Learning, Artificial Intelligence and Robotics. Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-030-85365-5.
Full text
3
Stamp, Mark, Mamoun Alazab, and Andrii Shalaginov, eds. Malware Analysis Using Artificial Intelligence and Deep Learning. Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-62582-5.
Full text
4
Roy, Sangita, Rajat Subhra Chakraborty, Jimson Mathew, Arka Prokash Mazumdar, and Sudeshna Chakraborty. Artificial Intelligence and Deep Learning for Computer Network. Chapman and Hall/CRC, 2023. http://dx.doi.org/10.1201/9781003212249.
Full text
5
Tache, Nicole, ed. Learning TensorFlow: A Guide to Building Deep Learning Systems. O'Reilly Media, 2017.
Find full text
6
Mohan Kumar, Dr S. Artificial Intelligence: Foundations, Applications, and the Generative Future. Magestic Technology Solutions (P) Ltd, Chennai, Tamil Nadu, India, 2025. https://doi.org/10.47716/978-93-92090-63-9.
Full textAbstract:
Artificial Intelligence (AI) is no longer confined to laboratories and theoretical models; it is now a driving force behind the digital transformation of society. Artificial Intelligence: Foundations, Applications, and the Generative Future provides an in-depth journey through AI’s essential principles, its wide-ranging applications, and the revolutionary impact of generative technologies. The book methodically builds knowledge from classical AI concepts like intelligent agents, search strategies, and knowledge representation, to advanced learning models including neural networks and machine learning algorithms. It culminates in an exploration of Generative AI—highlighting its transformative role in Industry 5.0, autonomous systems, and creative industries. Designed for both academic and professional audiences, this work offers not just understanding, but vision—preparing readers to navigate and shape the next frontier of AI evolution. Keywords: Artificial Intelligence, Machine Learning, Knowledge Representation, Neural Networks, Generative AI, Deep Learning, Industry 5.0, Intelligent Systems, Future of AI, Digital Transformation
9
Campesato, Oswald. Artificial Intelligence, Machine Learning, and Deep Learning. Mercury Learning & Information, 2020.
Find full text
10
Campesato, Oswald. Artificial Intelligence, Machine Learning, and Deep Learning. Mercury Learning & Information, 2020.
Find full textBook chapters on the topic "Artificial Intelligence; Deep learning; Representation learning"
1
Sharifirad, Sima, and Stan Matwin. "Deep Multi-cultural Graph Representation Learning." In Advances in Artificial Intelligence. Springer International Publishing, 2017. http://dx.doi.org/10.1007/978-3-319-57351-9_46.
Full text
2
Luger, George F. "Deep Learning: Introduction and Representations." In Artificial Intelligence: Principles and Practice. Springer Nature Switzerland, 2024. https://doi.org/10.1007/978-3-031-57437-5_17.
Full text
3
Loeffler, Christoffer, Felix Ott, Jonathan Ott, MaximilianP Oppelt, and Tobias Feigl. "Sequence-based Learning." In Unlocking Artificial Intelligence. Springer Nature Switzerland, 2024. http://dx.doi.org/10.1007/978-3-031-64832-8_2.
Full textAbstract:
AbstractLearning from time series data is an essential component in the AI landscape given the ubiquitous time-dependent data in real-world applications. To motivate the necessity of learning from time series data, we first introduce different applications, data sources, and properties. These can be as diverse as irregular and (non-)continuous time series data as well as streaming and spatio-temporal data. To introduce the mechanics of learning from time series data, we elaborate on the most renowned convolutional, recurrent and transformer architectures for learning from time series. Then, we discuss essential characteristics of learning with time series. Therefore, we explain deep metric learning, which learns feature representations that capture the similarity between time series data.We further describe time series similarity learning to extract representations that allow comparison between sequences of spatio-temporal data. In addition, we discuss the interpretability of learning methods on time series data that target safety, non-discrimination, and fairness.
4
Schmieg, Tobias, and Carsten Lanquillon. "Time Series Representation Learning: A Survey on Deep Learning Techniques for Time Series Forecasting." In Artificial Intelligence in HCI. Springer Nature Switzerland, 2024. http://dx.doi.org/10.1007/978-3-031-60606-9_25.
Full text
5
Leonardi, Giorgio, Stefania Montani, and Manuel Striani. "Deep Learning for Haemodialysis Time Series Classification." In Artificial Intelligence in Medicine: Knowledge Representation and Transparent and Explainable Systems. Springer International Publishing, 2019. http://dx.doi.org/10.1007/978-3-030-37446-4_5.
Full text
6
Srinivasan, Sriram, R. Vinayakumar, Ajay Arunachalam, Mamoun Alazab, and KP Soman. "DURLD: Malicious URL Detection Using Deep Learning-Based Character Level Representations." In Malware Analysis Using Artificial Intelligence and Deep Learning. Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-62582-5_21.
Full text
7
HekmatiAthar, SeyyedPooya, Letu Qingge, and Mohd Anwar. "Representation and Generation of Music: Incorporating Composers’ Perspectives into Deep Learning Models." In Advances and Trends in Artificial Intelligence. Theory and Applications. Springer Nature Singapore, 2024. http://dx.doi.org/10.1007/978-981-97-4677-4_20.
Full text
8
Yücel, Hikmet. "Effect of Representation of Information in the Input of Deep Learning on Prediction Success." In Artificial Intelligence and Applied Mathematics in Engineering Problems. Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-36178-5_60.
Full text
9
Saiod, Abdul Kader, and Darelle van Greunen. "The Impact of Deep Learning on the Semantic Machine Learning Representation." In Advanced Concepts, Methods, and Applications in Semantic Computing. IGI Global, 2021. http://dx.doi.org/10.4018/978-1-7998-6697-8.ch002.
Full textAbstract:
Deep learning (DL) is one of the core subsets of the semantic machine learning representations (SMLR) that impact on discovering multiple processing layers of non-linear big data (BD) transformations with high levels of abstraction concepts. The SMLR can unravel the concealed explanation characteristics and modifications of the heterogeneous data sources that are intertwined for further artificial intelligence (AI) implementations. Deep learning impacts high-level abstractions in data by deploying hierarchical architectures. It is practically challenging to model big data representations, which impacts on data and knowledge-based representations. Encouraged by deep learning, the formal knowledge representation has the potential to influence the SMLR process. Deep learning architecture is capable of modelling efficient big data representations for further artificial intelligence and SMLR tasks. This chapter focuses on how deep learning impacts on defining deep transfer learning, category, and works based on the techniques used on semantic machine learning representations.
10
Do, Nguyet Quang, Ali Selamat, Kok Cheng Lim, and Ondrej Krejcar. "Malicious URL Detection with Distributed Representation and Deep Learning." In Frontiers in Artificial Intelligence and Applications. IOS Press, 2022. http://dx.doi.org/10.3233/faia220248.
Full textAbstract:
There exist numerous solutions to detect malicious URLs based on Natural Language Processing and machine learning technologies. However, there is a lack of comparative analysis among approaches using distributed representation and deep learning. To solve this problem, this paper performs a comparative study on phishing URL detection based on text embedding and deep learning algorithms. Specifically, character-level and word-level embedding were combined to learn the feature representations from the webpage URLs. In addition, three deep learning models, including Convolutional Neural Network (CNN), Bidirectional Gated Recurrent Unit (BiGRU), and Bidirectional Long Short-Term Memory (BiLSTM), were constructed for effective classification of phishing websites. Several experiments were conducted and various evaluation metrics were used to assess the performance of these deep learning models. The findings obtained from the experiments indicated that the combination of the character-level and word-level embedding approach produced better results than the individual text representation methods. Also, the CNN-based model outperformed the other two deep learning algorithms in terms of both detection accuracy and execution time.
Conference papers on the topic "Artificial Intelligence; Deep learning; Representation learning"
1
Zhu, Hanhua. "Generalized Representation Learning Methods for Deep Reinforcement Learning." In Twenty-Ninth International Joint Conference on Artificial Intelligence and Seventeenth Pacific Rim International Conference on Artificial Intelligence {IJCAI-PRICAI-20}. International Joint Conferences on Artificial Intelligence Organization, 2020. http://dx.doi.org/10.24963/ijcai.2020/748.
Full textAbstract:
Deep reinforcement learning (DRL) increases the successful applications of reinforcement learning (RL) techniques but also brings challenges such as low sample efficiency. In this work, I propose generalized representation learning methods to obtain compact state space suitable for RL from a raw observation state. I expect my new methods will increase sample efficiency of RL by understandable representations of state and therefore improve the performance of RL.
2
Li, Sheng, and Handong Zhao. "A Survey on Representation Learning for User Modeling." In Twenty-Ninth International Joint Conference on Artificial Intelligence and Seventeenth Pacific Rim International Conference on Artificial Intelligence {IJCAI-PRICAI-20}. International Joint Conferences on Artificial Intelligence Organization, 2020. http://dx.doi.org/10.24963/ijcai.2020/695.
Full textAbstract:
Artificial intelligent systems are changing every aspect of our daily life. In the past decades, numerous approaches have been developed to characterize user behavior, in order to deliver personalized experience to users in scenarios like online shopping or movie recommendation. This paper presents a comprehensive survey of recent advances in user modeling from the perspective of representation learning. In particular, we formulate user modeling as a process of learning latent representations for users. We discuss both the static and sequential representation learning methods for the purpose of user modeling, and review representative approaches in each category, such as matrix factorization, deep collaborative filtering, and recurrent neural networks. Both shallow and deep learning methods are reviewed and discussed. Finally, we conclude this survey and discuss a number of open research problems that would inspire further research in this field.
3
Zhu, Mingrui, Nannan Wang, Xinbo Gao, and Jie Li. "Deep Graphical Feature Learning for Face Sketch Synthesis." In Twenty-Sixth International Joint Conference on Artificial Intelligence. International Joint Conferences on Artificial Intelligence Organization, 2017. http://dx.doi.org/10.24963/ijcai.2017/500.
Full textAbstract:
The exemplar-based face sketch synthesis method generally contains two steps: neighbor selection and reconstruction weight representation. Pixel intensities are widely used as features by most of the existing exemplar-based methods, which lacks of representation ability and robustness to light variations and clutter backgrounds. We present a novel face sketch synthesis method combining generative exemplar-based method and discriminatively trained deep convolutional neural networks (dCNNs) via a deep graphical feature learning framework. Our method works in both two steps by using deep discriminative representations derived from dCNNs. Instead of using it directly, we boost its representation capability by a deep graphical feature learning framework. Finally, the optimal weights of deep representations and optimal reconstruction weights for face sketch synthesis can be obtained simultaneously. With the optimal reconstruction weights, we can synthesize high quality sketches which is robust against light variations and clutter backgrounds. Extensive experiments on public face sketch databases show that our method outperforms state-of-the-art methods, in terms of both synthesis quality and recognition ability.
4
Miyajima, Ryoga, and Katsuhide Fujita. "Deep Reinforcement Learning Framework with Representation Learning for Concurrent Negotiation." In 16th International Conference on Agents and Artificial Intelligence. SCITEPRESS - Science and Technology Publications, 2024. http://dx.doi.org/10.5220/0012336000003636.
Full text
5
Zhang, Puzhao, Maoguo Gong, Hui Zhang, and Jia Liu. "DRLnet: Deep Difference Representation Learning Network and An Unsupervised Optimization Framework." In Twenty-Sixth International Joint Conference on Artificial Intelligence. International Joint Conferences on Artificial Intelligence Organization, 2017. http://dx.doi.org/10.24963/ijcai.2017/477.
Full textAbstract:
Change detection and analysis (CDA) is an important research topic in the joint interpretation of spatial-temporal remote sensing images. The core of CDA is to effectively represent the difference and measure the difference degree between bi-temporal images. In this paper, we propose a novel difference representation learning network (DRLnet) and an effective optimization framework without any supervision. Difference measurement, difference representation learning and unsupervised clustering are combined as a single model, i.e., DRLnet, which is driven to learn clustering-friendly and discriminative difference representations (DRs) for different types of changes. Further, DRLnet is extended into a recurrent learning framework to update and reuse limited training samples and prevent the semantic gaps caused by the saltation in the number of change types from over-clustering stage to the desired one. Experimental results identify the effectiveness of the proposed framework.
6
Luo, Xufang, Qi Meng, Di He, Wei Chen, and Yunhong Wang. "I4R: Promoting Deep Reinforcement Learning by the Indicator for Expressive Representations." In Twenty-Ninth International Joint Conference on Artificial Intelligence and Seventeenth Pacific Rim International Conference on Artificial Intelligence {IJCAI-PRICAI-20}. International Joint Conferences on Artificial Intelligence Organization, 2020. http://dx.doi.org/10.24963/ijcai.2020/370.
Full textAbstract:
Learning expressive representations is always crucial for well-performed policies in deep reinforcement learning (DRL). Different from supervised learning, in DRL, accurate targets are not always available, and some inputs with different actions only have tiny differences, which stimulates the demand for learning expressive representations. In this paper, firstly, we empirically compare the representations of DRL models with different performances. We observe that the representations of a better state extractor (SE) are more scattered than a worse one when they are visualized. Thus, we investigate the singular values of representation matrix, and find that, better SEs always correspond to smaller differences among these singular values. Next, based on such observations, we define an indicator of the representations for DRL model, which is the Number of Significant Singular Values (NSSV) of a representation matrix. Then, we propose I4R algorithm, to improve DRL algorithms by adding the corresponding regularization term to enhance the NSSV. Finally, we apply I4R to both policy gradient and value based algorithms on Atari games, and the results show the superiority of our proposed method.
7
Li, Ya, Xinmei Tian, Xu Shen, and Dacheng Tao. "Classification and Representation Joint Learning via Deep Networks." In Twenty-Sixth International Joint Conference on Artificial Intelligence. International Joint Conferences on Artificial Intelligence Organization, 2017. http://dx.doi.org/10.24963/ijcai.2017/308.
Full textAbstract:
Deep learning has been proven to be effective for classification problems. However, the majority of previous works trained classifiers by considering only class label information and ignoring the local information from the spatial distribution of training samples. In this paper, we propose a deep learning framework that considers both class label information and local spatial distribution information between training samples. A two-channel network with shared weights is used to measure the local distribution. The classification performance can be improved with more detailed information provided by the local distribution, particularly when the training samples are insufficient. Additionally, the class label information can help to learn better feature representations compared with other feature learning methods that use only local distribution information between samples. The local distribution constraint between sample pairs can also be viewed as a regularization of the network, which can efficiently prevent the overfitting problem. Extensive experiments are conducted on several benchmark image classification datasets, and the results demonstrate the effectiveness of our proposed method.
8
Chen, Shaoxiang, Ting Yao, and Yu-Gang Jiang. "Deep Learning for Video Captioning: A Review." In Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}. International Joint Conferences on Artificial Intelligence Organization, 2019. http://dx.doi.org/10.24963/ijcai.2019/877.
Full textAbstract:
Deep learning has achieved great successes in solving specific artificial intelligence problems recently. Substantial progresses are made on Computer Vision (CV) and Natural Language Processing (NLP). As a connection between the two worlds of vision and language, video captioning is the task of producing a natural-language utterance (usually a sentence) that describes the visual content of a video. The task is naturally decomposed into two sub-tasks. One is to encode a video via a thorough understanding and learn visual representation. The other is caption generation, which decodes the learned representation into a sequential sentence, word by word. In this survey, we first formulate the problem of video captioning, then review state-of-the-art methods categorized by their emphasis on vision or language, and followed by a summary of standard datasets and representative approaches. Finally, we highlight the challenges which are not yet fully understood in this task and present future research directions.
9
Davari, Mohammadjavad, Khalil Alipour, and Alireza Hadi. "Alleviating Credit Assignment problem using deep representation learning with application to Push Recovery learning." In 2017 Artificial Intelligence and Robotics (IRANOPEN). IEEE, 2017. http://dx.doi.org/10.1109/rios.2017.7956452.
Full text
10
Dumancic, Sebastijan, Tias Guns, Wannes Meert, and Hendrik Blockeel. "Learning Relational Representations with Auto-encoding Logic Programs." In Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}. International Joint Conferences on Artificial Intelligence Organization, 2019. http://dx.doi.org/10.24963/ijcai.2019/842.
Full textAbstract:
Deep learning methods capable of handling relational data have proliferated over the past years. In contrast to traditional relational learning methods that leverage first-order logic for representing such data, these methods aim at re-representing symbolic relational data in Euclidean space. They offer better scalability, but can only approximate rich relational structures and are less flexible in terms of reasoning. This paper introduces a novel framework for relational representation learning that combines the best of both worlds. This framework, inspired by the auto-encoding principle, uses first-order logic as a data representation language, and the mapping between the the original and latent representation is done by means of logic programs instead of neural networks. We show how learning can be cast as a constraint optimisation problem for which existing solvers can be used. The use of logic as a representation language makes the proposed framework more accurate (as the representation is exact, rather than approximate), more flexible, and more interpretable than deep learning methods. We experimentally show that these latent representations are indeed beneficial in relational learning tasks.
Reports on the topic "Artificial Intelligence; Deep learning; Representation learning"
1
Varastehpour, Soheil, Hamid Sharifzadeh, and Iman Ardekani. A Comprehensive Review of Deep Learning Algorithms. Unitec ePress, 2021. http://dx.doi.org/10.34074/ocds.092.
Full textAbstract:
Deep learning algorithms are a subset of machine learning algorithms that aim to explore several levels of the distributed representations from the input data. Recently, many deep learning algorithms have been proposed to solve traditional artificial intelligence problems. In this review paper, some of the up-to-date algorithms of this topic in the field of computer vision and image processing are reviewed. Following this, a brief overview of several different deep learning methods and their recent developments are discussed.
2
Cerulli, Giovanni. Deep Learning and AI for Research in Python. Instats Inc., 2023. http://dx.doi.org/10.61700/g6nxp3uxsvu3l469.
Full textAbstract:
This seminar is an introduction to Deep Learning and Artificial Intelligence methods for the social, economic, and health sciences using Python. After introducing the subject, the seminar will cover the following methods: (i) Feedforward Neural Networks (FNNs) (ii) Convolutional Neural Networks (CNNs); and (iii) Recursive Neural Networks (RNNs). The course will offer various instructional examples using real datasets in Python. An Instats certificate of completion is provided at the end of the seminar, and 2 ECTS equivalent points are offered.
3
Mazari, Mehran, Yahaira Nava-Gonzalez, Ly Jacky Nhiayi, and Mohamad Saleh. Smart Highway Construction Site Monitoring Using Artificial Intelligence. Mineta Transportation Institute, 2025. https://doi.org/10.31979/mti.2025.2336.
Full textAbstract:
Construction is a large sector of the economy and plays a significant role in creating economic growth and national development,and construction of transportation infrastructure is critical. This project developed a method to detect, classify, monitor, and track objects during the construction, maintenance, and rehabilitation of transportation infrastructure by using artificial intelligence and a deep learning approach. This study evaluated the performance of AI and deep learning algorithms to compare their performance in detecting and classifying the equipment in various construction scenes. Our goal was to find the optimized balance between the model capabilities in object detection and memory processing requirements. Due to the lack of a comprehensive image database specifically developed for transportation infrastructure construction projects, the first portion of this study focused on preparing a comprehensive database of annotated images for various classes of equipment and machinery that are commonly used in roadway construction and rehabilitation projects. The second part of the project focused on training the deep learning models and improving the accuracy of the classification and detection algorithms. The outcomes of the trained and improved deep learning classification model were promising in terms of the precision and accuracy of the model in detecting specific objects at a highway construction site. It should be noted that the scope of this project was limited to the image and video data recorded from the ground-level and cannot be extended to Uncrewed Aerial System (UAS) data. This study provides valuable insights on the potentials of AI and deep learning to improve the monitoring and thus safety and efficiency of transportation infrastructure construction.
4
Pourhomayoun, Mohammad. Automatic Traffic Monitoring and Management for Pedestrian and Cyclist Safety Using Deep Learning and Artificial Intelligence. Mineta Transportation Institute, 2020. http://dx.doi.org/10.31979/mti.2020.1808.
Full text
5
Rinuado, Christina, William Leonard, Christopher Morey, Theresa Coumbe, Jaylen Hopson, and Robert Hilborn. Artificial intelligence (AI)–enabled wargaming agent training. Engineer Research and Development Center (U.S.), 2024. http://dx.doi.org/10.21079/11681/48419.
Full textAbstract:
Fiscal Year 2021 (FY21) work from the Engineer Research and Development Center Institute for Systems Engineering Research lever-aged deep reinforcement learning to develop intelligent systems (red team agents) capable of exhibiting credible behavior within a military course of action wargaming maritime framework infrastructure. Building from the FY21 research, this research effort sought to explore options to improve upon the wargaming framework infrastructure and to investigate opportunities to improve artificial intelligence (AI) agent behavior. Wargaming framework infrastructure enhancements included updates related to supporting agent training, leveraging high-performance computing resources, and developing infrastructure to support AI versus AI agent training and gameplay. After evaluating agent training across different algorithm options, Deep Q-Network–trained agents performed better compared to those trained with Advantage Actor Critic or Proximal Policy Optimization algorithms. Experimentation in varying scenarios revealed acceptable performance from agents trained in the original baseline scenario. By training a blue agent against a previously trained red agent, researchers successfully demonstrated the AI versus AI training and gameplay capability. Observing results from agent gameplay revealed the emergence of behavior indicative of two principles of war, which were economy of force and mass.
6
Pasupuleti, Murali Krishna. Quantum-Enhanced Machine Learning: Harnessing Quantum Computing for Next-Generation AI Systems. National Education Services, 2025. https://doi.org/10.62311/nesx/rrv125.
Full textAbstract:
Abstract Quantum-enhanced machine learning (QML) represents a paradigm shift in artificial intelligence by integrating quantum computing principles to solve complex computational problems more efficiently than classical methods. By leveraging quantum superposition, entanglement, and parallelism, QML has the potential to accelerate deep learning training, optimize combinatorial problems, and enhance feature selection in high-dimensional spaces. This research explores foundational quantum computing concepts relevant to AI, including quantum circuits, variational quantum algorithms, and quantum kernel methods, while analyzing their impact on neural networks, generative models, and reinforcement learning. Hybrid quantum-classical AI architectures, which combine quantum subroutines with classical deep learning models, are examined for their ability to provide computational advantages in optimization and large-scale data processing. Despite the promise of quantum AI, challenges such as qubit noise, error correction, and hardware scalability remain barriers to full-scale implementation. This study provides an in-depth evaluation of quantum-enhanced AI, highlighting existing applications, ongoing research, and future directions in quantum deep learning, autonomous systems, and scientific computing. The findings contribute to the development of scalable quantum machine learning frameworks, offering novel solutions for next-generation AI systems across finance, healthcare, cybersecurity, and robotics. Keywords Quantum machine learning, quantum computing, artificial intelligence, quantum neural networks, quantum kernel methods, hybrid quantum-classical AI, variational quantum algorithms, quantum generative models, reinforcement learning, quantum optimization, quantum advantage, deep learning, quantum circuits, quantum-enhanced AI, quantum deep learning, error correction, quantum-inspired algorithms, quantum annealing, probabilistic computing.
7
Alhasson, Haifa F., and Shuaa S. Alharbi. New Trends in image-based Diabetic Foot Ucler Diagnosis Using Machine Learning Approaches: A Systematic Review. INPLASY - International Platform of Registered Systematic Review and Meta-analysis Protocols, 2022. http://dx.doi.org/10.37766/inplasy2022.11.0128.
Full textAbstract:
Review question / Objective: A significant amount of research has been conducted to detect and recognize diabetic foot ulcers (DFUs) using computer vision methods, but there are still a number of challenges. DFUs detection frameworks based on machine learning/deep learning lack systematic reviews. With Machine Learning (ML) and Deep learning (DL), you can improve care for individuals at risk for DFUs, identify and synthesize evidence about its use in interventional care and management of DFUs, and suggest future research directions. Information sources: A thorough search of electronic databases such as Science Direct, PubMed (MIDLINE), arXiv.org, MDPI, Nature, Google Scholar, Scopus and Wiley Online Library was conducted to identify and select the literature for this study (January 2010-January 01, 2023). It was based on the most popular image-based diagnosis targets in DFu such as segmentation, detection and classification. Various keywords were used during the identification process, including artificial intelligence in DFu, deep learning, machine learning, ANNs, CNNs, DFu detection, DFu segmentation, DFu classification, and computer-aided diagnosis.
8
Rinaudo, Christina, William Leonard, Jaylen Hopson, Christopher Morey, Robert Hilborn, and Theresa Coumbe. Enabling understanding of artificial intelligence (AI) agent wargaming decisions through visualizations. Engineer Research and Development Center (U.S.), 2024. http://dx.doi.org/10.21079/11681/48418.
Full textAbstract:
The process to develop options for military planning course of action (COA) development and analysis relies on human subject matter expertise. Analyzing COAs requires examining several factors and understanding complex interactions and dependencies associated with actions, reactions, proposed counteractions, and multiple reasonable outcomes. In Fiscal Year 2021, the Institute for Systems Engineering Research team completed efforts resulting in a wargaming maritime framework capable of training an artificial intelligence (AI) agent with deep reinforcement learning (DRL) techniques within a maritime scenario where the AI agent credibly competes against blue agents in gameplay. However, a limitation of using DRL for agent training relates to the transparency of how the AI agent makes decisions. If leaders were to rely on AI agents for COA development or analysis, they would want to understand those decisions. In or-der to support increased understanding, researchers engaged with stakeholders to determine visualization requirements and developed initial prototypes for stakeholder feedback in order to support increased understanding of AI-generated decisions and recommendations. This report describes the prototype visualizations developed to support the use case of a mission planner and an AI agent trainer. The prototypes include training results charts, heat map visualizations of agent paths, weight matrix visualizations, and ablation testing graphs.
9
Marsden, Eric, and Véronique Steyer. Artificial intelligence and safety management: an overview of key challenges. Foundation for an Industrial Safety Culture, 2025. https://doi.org/10.57071/iae290.
Full textAbstract:
Artificial intelligence based on deep learning, along with big data analysis, has in recent years been the subject of rapid scientific and technological advances. These technologies are increasingly being integrated into various work environments with the aim of enhancing performance and productivity. This dimension of the digital transformation of businesses and regulatory authorities presents both significant opportunities and potential risks for industrial safety management practices. While there are numerous expected benefits, such as the ability to process large volumes of reliability data or unstructured natural language incident reports, the structural opacity of large neural networks, their non-deterministic nature, and their capacity to learn from new data mean that traditional safety assurance techniques used for conventional software are not applicable. Additionally, the expansion of the scope of automatable tasks and the gradual move towards work collectives that are composed of human operators who collaborate with various intelligent machines and agents introduce new variables that must be considered alongside and integrated with the organizational and human factors of safety. What are the main challenges posed by these new technologies in terms of skills management, worker well-being, privacy protection, and the pursuit of performance that aligns with societal expectations? What changes are required in how we conceptualize the safety of high-stakes activities, how we demonstrate and verify the absence of unacceptable risks, and anticipate potential deviations? This document provides a concise overview of the most recent available information, contextualized by decades of research on automation in high-hazard systems. It focuses specifically on the projected impacts for high-hazard industries and infrastructures over the next ten years.
10
Pasupuleti, Murali Krishna. Stochastic Computation for AI: Bayesian Inference, Uncertainty, and Optimization. National Education Services, 2025. https://doi.org/10.62311/nesx/rriv325.
Full textAbstract:
Abstract: Stochastic computation is a fundamental approach in artificial intelligence (AI) that enables probabilistic reasoning, uncertainty quantification, and robust decision-making in complex environments. This research explores the theoretical foundations, computational techniques, and real-world applications of stochastic methods, focusing on Bayesian inference, Monte Carlo methods, stochastic optimization, and uncertainty-aware AI models. Key topics include probabilistic graphical models, Markov Chain Monte Carlo (MCMC), variational inference, stochastic gradient descent (SGD), and Bayesian deep learning. These techniques enhance AI's ability to handle uncertain, noisy, and high-dimensional data while ensuring scalability, interpretability, and trustworthiness in applications such as robotics, financial modeling, autonomous systems, and healthcare AI. Case studies demonstrate how stochastic computation improves self-driving car navigation, financial risk assessment, personalized medicine, and reinforcement learning-based automation. The findings underscore the importance of integrating probabilistic modeling with deep learning, reinforcement learning, and optimization techniques to develop AI systems that are more adaptable, scalable, and uncertainty-aware. Keywords Stochastic computation, Bayesian inference, probabilistic AI, Monte Carlo methods, Markov Chain Monte Carlo (MCMC), variational inference, uncertainty quantification, stochastic optimization, Bayesian deep learning, reinforcement learning, probabilistic graphical models, stochastic gradient descent (SGD), uncertainty-aware AI, probabilistic reasoning, risk assessment, AI in robotics, AI in finance, AI in healthcare, decision-making under uncertainty, trustworthiness in AI, scalable AI, interpretable AI.