Journal articles: '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 text

Abstract:

<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>

APA, Harvard, Vancouver, ISO, and other styles

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

APA, Harvard, Vancouver, ISO, and other styles

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 text

Abstract:

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.

APA, Harvard, Vancouver, ISO, and other styles

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 text

Abstract:

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.

APA, Harvard, Vancouver, ISO, and other styles

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 text

Abstract:

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.

APA, Harvard, Vancouver, ISO, and other styles

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

APA, Harvard, Vancouver, ISO, and other styles

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

APA, Harvard, Vancouver, ISO, and other styles

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 text

Abstract:

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.

APA, Harvard, Vancouver, ISO, and other styles

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 text

Abstract:

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.

APA, Harvard, Vancouver, ISO, and other styles

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 text

Abstract:

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.

APA, Harvard, Vancouver, ISO, and other styles

11

Bandaru, Satish Babu, Natarajasivan Deivarajan, and Rama Mohan Babu Gatram. "Investigations on Deep Learning Techniques for Analysing Mammograms." Revue d'Intelligence Artificielle 36, no. 3 (2022): 451–57. http://dx.doi.org/10.18280/ria.360313.

Full text

Abstract:

Mammograms have been acknowledged as one of the most reliable screening tools as well as a key diagnostic mechanism for early breast cancer detection. Though mammography is a valuable screening tool for detecting malignant growth in breasts, its competence as a diagnostic tool is heavily reliant on the radiologists’ understanding. Automated systems are now widely used for detection of breast cancer. Image processing techniques were widely used in automated systems for classifying mammograms. Of late with the advent of deep learning (DL) where images can be processed directly for classification, the DL is widely researched for medical image classification. Basically, DL techniques are representation-learning methods which aid in understanding data like sounds, images as well as texts. DL algorithms have the ability to learn multiple levels of representation as well as abstraction. Residual network (ResNet) is given due consideration as a kind of highly advanced Convolutional Neural Networks (CNNs). This work has offered a potential application of Visual Geometry Group (VGG), Residual network (ResNet) and Inception based CNN model for differentiating the mammograms into the abnormal class and the normal class. Experimental results demonstrated that the deep learners are effective for classifying mammograms and Inception deep learner achieved the best accuracy of 91.49%.

APA, Harvard, Vancouver, ISO, and other styles

12

Sakai, Akira, Masaaki Komatsu, Reina Komatsu, et al. "Medical Professional Enhancement Using Explainable Artificial Intelligence in Fetal Cardiac Ultrasound Screening." Biomedicines 10, no. 3 (2022): 551. http://dx.doi.org/10.3390/biomedicines10030551.

Full text

Abstract:

Diagnostic support tools based on artificial intelligence (AI) have exhibited high performance in various medical fields. However, their clinical application remains challenging because of the lack of explanatory power in AI decisions (black box problem), making it difficult to build trust with medical professionals. Nevertheless, visualizing the internal representation of deep neural networks will increase explanatory power and improve the confidence of medical professionals in AI decisions. We propose a novel deep learning-based explainable representation “graph chart diagram” to support fetal cardiac ultrasound screening, which has low detection rates of congenital heart diseases due to the difficulty in mastering the technique. Screening performance improves using this representation from 0.966 to 0.975 for experts, 0.829 to 0.890 for fellows, and 0.616 to 0.748 for residents in the arithmetic mean of area under the curve of a receiver operating characteristic curve. This is the first demonstration wherein examiners used deep learning-based explainable representation to improve the performance of fetal cardiac ultrasound screening, highlighting the potential of explainable AI to augment examiner capabilities.

APA, Harvard, Vancouver, ISO, and other styles

13

Yan, Fangxu, Jianhui Wang, and Wei Li. "Research on the Application of Deep Learning in Natural Language Processing." Frontiers in Computing and Intelligent Systems 9, no. 2 (2024): 56–58. http://dx.doi.org/10.54097/m9sxpv44.

Full text

Abstract:

Deep learning is a kind of machine learning, which is the necessary path to realize artificial intelligence. The application of deep learning in the field of natural language processing has gone far beyond the limitations of traditional methods, showing unparalleled advantages such as automatically learning abstract features from the original data to form preciser representation. This paper aims to analyze the application of deep learning in natural language processing, and provides reference for the follow-up research and development in this field.

APA, Harvard, Vancouver, ISO, and other styles

14

Tedjopurnomo, David Alexander, Xiucheng Li, Zhifeng Bao, Gao Cong, Farhana Choudhury, and A. K. Qin. "Similar Trajectory Search with Spatio-Temporal Deep Representation Learning." ACM Transactions on Intelligent Systems and Technology 12, no. 6 (2021): 1–26. http://dx.doi.org/10.1145/3466687.

Full text

Abstract:

Similar trajectory search is a crucial task that facilitates many downstream spatial data analytic applications. Despite its importance, many of the current literature focus solely on the trajectory’s spatial similarity while neglecting the temporal information. Additionally, the few papers that use both the spatial and temporal features based their approach on a traditional point-to-point comparison. These methods model the importance of the spatial and temporal aspect of the data with only a single, pre-defined balancing factor for all trajectories, even though the relative spatial and temporal balance can change from trajectory to trajectory. In this article, we propose the first spatio-temporal, deep-representation-learning-based approach to similar trajectory search. Experiments show that utilizing both features offers significant improvements over existing point-to-point comparison and deep-representation-learning approach. We also show that our deep neural network approach is faster and performs more consistently compared to the point-to-point comparison approaches.

APA, Harvard, Vancouver, ISO, and other styles

15

O’Mahony, Niall, Sean Campbell, Lenka Krpalkova, Anderson Carvalho, Joseph Walsh, and Daniel Riordan. "Representation Learning for Fine-Grained Change Detection." Sensors 21, no. 13 (2021): 4486. http://dx.doi.org/10.3390/s21134486.

Full text

Abstract:

Fine-grained change detection in sensor data is very challenging for artificial intelligence though it is critically important in practice. It is the process of identifying differences in the state of an object or phenomenon where the differences are class-specific and are difficult to generalise. As a result, many recent technologies that leverage big data and deep learning struggle with this task. This review focuses on the state-of-the-art methods, applications, and challenges of representation learning for fine-grained change detection. Our research focuses on methods of harnessing the latent metric space of representation learning techniques as an interim output for hybrid human-machine intelligence. We review methods for transforming and projecting embedding space such that significant changes can be communicated more effectively and a more comprehensive interpretation of underlying relationships in sensor data is facilitated. We conduct this research in our work towards developing a method for aligning the axes of latent embedding space with meaningful real-world metrics so that the reasoning behind the detection of change in relation to past observations may be revealed and adjusted. This is an important topic in many fields concerned with producing more meaningful and explainable outputs from deep learning and also for providing means for knowledge injection and model calibration in order to maintain user confidence.

APA, Harvard, Vancouver, ISO, and other styles

16

Mandhasiya, Dwi Guna, Hendri Murfi, and Alhadi Bustamam. "The hybrid of BERT and deep learning models for Indonesian sentiment analysis." Indonesian Journal of Electrical Engineering and Computer Science 33, no. 1 (2024): 591–602. https://doi.org/10.11591/ijeecs.v33.i1.pp591-602.

Full text

Abstract:

Artificial intelligence (AI) is one example of how data science innovation has advanced quickly in recent years and has greatly improved human existence. Neural networks, which are a type of machine learning model, are a fundamental component of deep learning in the field of AI. Deep learning models can carry out feature extraction and classification tasks in a single design because of their numerous neural network layers. Modern machine learning algorithms have been shown to perform worse than this model on tasks including text classification, audio recognition, imaginary, and pattern recognition. Deep learning models have outperformed AI-based methods in sentiment analysis and other text categorization tasks. Text data can originate from a number of places, including social media. Sentiment analysis is the computational examination of textual expressions of ideas and feelings. This study employs the convolutional neural network (CNN), long-short term memory (LSTM), CNN-LSTM, and LSTM-CNN models in a deep learning framework using bidirectional encoder representations from transformers (BERT) data representation to assess the performance of machine learning. The implementation of the model utilises YouTube discussion data pertaining to political films associated with the Indonesian presidential election of 2024. Confusion metrics, including as accuracy, precision, and recall, are then used to analyse the model’s performance.

APA, Harvard, Vancouver, ISO, and other styles

17

Alam, M., L. Vidyaratne, and K. M. Iftekharuddin. "Novel deep generative simultaneous recurrent model for efficient representation learning." Neural Networks 107 (November 2018): 12–22. http://dx.doi.org/10.1016/j.neunet.2018.04.020.

Full text

APA, Harvard, Vancouver, ISO, and other styles

18

Kasabov, Nikola K. "Spiking neural networks for deep learning and knowledge representation: Editorial." Neural Networks 119 (November 2019): 341–42. http://dx.doi.org/10.1016/j.neunet.2019.08.019.

Full text

APA, Harvard, Vancouver, ISO, and other styles

19

Löffler, Christoffer, Luca Reeb, Daniel Dzibela, et al. "Deep Siamese Metric Learning: A Highly Scalable Approach to Searching Unordered Sets of Trajectories." ACM Transactions on Intelligent Systems and Technology 13, no. 1 (2022): 1–23. http://dx.doi.org/10.1145/3465057.

Full text

Abstract:

This work proposes metric learning for fast similarity-based scene retrieval of unstructured ensembles of trajectory data from large databases. We present a novel representation learning approach using Siamese Metric Learning that approximates a distance preserving low-dimensional representation and that learns to estimate reasonable solutions to the assignment problem. To this end, we employ a Temporal Convolutional Network architecture that we extend with a gating mechanism to enable learning from sparse data, leading to solutions to the assignment problem exhibiting varying degrees of sparsity. Our experimental results on professional soccer tracking data provides insights on learned features and embeddings, as well as on generalization, sensitivity, and network architectural considerations. Our low approximation errors for learned representations and the interactive performance with retrieval times several magnitudes smaller shows that we outperform previous state of the art.

APA, Harvard, Vancouver, ISO, and other styles

20

Mao, Zhi, and Mingfang Li. "Artificial intelligence and cognitive diagnosis based teaching resource recommendation algorithm." PeerJ Computer Science 9 (November 9, 2023): e1594. http://dx.doi.org/10.7717/peerj-cs.1594.

Full text

Abstract:

In the realm of advanced technology, deep learning capabilities are harnessed to analyze and predict novel data, once it has absorbed existing information. When applied to the sphere of education, this transformative technology becomes a catalyst for innovation and reform, leading to advancements in teaching modes, methodologies, and curricula. In light of these possibilities, the application of deep learning technology to teaching resource recommendations is explored in this article. Within the context of the study, a bespoke recommendation algorithm for teaching resources is devised, drawing upon the integration of deep learning and cognitive diagnosis (ADCF). This intricately constructed model consists of two core elements: the Multi-layer Perceptron (MLP) and the Generalized Matrix Factorization (GMF), operating cohesively through stages of linear representation and nonlinear learning of the interaction function. The empirical analysis reveals that the ADCF model achieves 0.626 and 0.339 in the hits ratio (HR) and the Normalized Discounted Cumulative Gain (NDCG) respectively due to the traditional model, signifying its potential to add significant value to the domain of teaching resource recommendations.

APA, Harvard, Vancouver, ISO, and other styles

21

Yuan, Ye, Guangxu Xun, Qiuling Suo, Kebin Jia, and Aidong Zhang. "Wave2Vec: Deep representation learning for clinical temporal data." Neurocomputing 324 (January 2019): 31–42. http://dx.doi.org/10.1016/j.neucom.2018.03.074.

Full text

APA, Harvard, Vancouver, ISO, and other styles

22

Makhmudova, Shakhzoda Yorkinovna, and Barno Abdunabiyevna Sharopova. "ARTIFICIAL INTELLIGENCE ALGORITHMS IN FACE RECOGNITION AND OBJECT DETECTION." Innovative Development in Educational Activities 3, no. 4 (2024): 146–50. https://doi.org/10.5281/zenodo.10726236.

Full text

Abstract:

<em>Facial recognition is a well-established and popular field in Computer Vision, especially with advancements in deep learning and data sets. Deep facial recognition has made significant progress and is widely applied in real-world scenarios. A complete facial recognition system involves three main components: facial recognition, orientation, and representation. This system detects faces, aligns them to a standard view, and extracts features for recognition using deep convolutional neural networks. This article provides a detailed overview of the latest advancements in these areas, showing how deep learning has greatly enhanced their abilities. Object detection in machine vision is a challenging area that requires significant improvements. While image classification accuracy is nearing 2.25%, surpassing human performance, object detection algorithms are still in the early stages. Current algorithms achieve only 40.8 MAPS on modern objects, so careful dataset selection is crucial for optimal results.</em>

APA, Harvard, Vancouver, ISO, and other styles

23

Yao, Di, Chao Zhang, Zhihua Zhu, et al. "Learning deep representation for trajectory clustering." Expert Systems 35, no. 2 (2018): e12252. http://dx.doi.org/10.1111/exsy.12252.

Full text

APA, Harvard, Vancouver, ISO, and other styles

24

Mody, Rohit, Debabrata Dash, and Deepanshu Mody. "Artificial intelligence in coronary physiology: where do we stand?" Journal of Transcatheter Interventions 30 (October 28, 2022): 1–9. http://dx.doi.org/10.31160/jotci202230a20220009.

Full text

Abstract:

The use of invasive coronary physiology to select individuals for coronary revascularization has been established in current guidelines for the management of stable coronary artery disease. Compared to angiography alone, coronary physiology has been proven to improve clinical outcomes and cost-effectiveness in the revascularization process. Randomized controlled trials, however, have questioned the efficacy of ischemia testing in selecting individuals for revascularization. After an angiographically successful percutaneous coronary intervention, 20 to 40% of patients experienced persistent or recurrent angina. Artificial intelligence is defined as the usage of various algorithms and computational concepts to perform the complex tasks in an efficient manner. It can be classified into two types: unsupervised and supervised approaches. Supervised learning is majorly used for the regression and classification tasks, and in this optimized mapping between output variables and paired input is carried out to perform the tasks. In contrast to this, unsupervised learning works in the different manner. In unsupervised learning, output variables data is not available and further clusters and relations between input data are found out by using the various algorithms. To acquire more abstract representation of data, deep learning technology, which uses the multilayer neural networks, dominates the artificial learning nowadays.

APA, Harvard, Vancouver, ISO, and other styles

25

Huan, Jeow Li, Arif Ahmed Sekh, Chai Quek, and Dilip K. Prasad. "Emotionally charged text classification with deep learning and sentiment semantic." Neural Computing and Applications 34, no. 3 (2021): 2341–51. http://dx.doi.org/10.1007/s00521-021-06542-1.

Full text

Abstract:

AbstractText classification is one of the widely used phenomena in different natural language processing tasks. State-of-the-art text classifiers use the vector space model for extracting features. Recent progress in deep models, recurrent neural networks those preserve the positional relationship among words achieve a higher accuracy. To push text classification accuracy even higher, multi-dimensional document representation, such as vector sequences or matrices combined with document sentiment, should be explored. In this paper, we show that documents can be represented as a sequence of vectors carrying semantic meaning and classified using a recurrent neural network that recognizes long-range relationships. We show that in this representation, additional sentiment vectors can be easily attached as a fully connected layer to the word vectors to further improve classification accuracy. On the UCI sentiment labelled dataset, using the sequence of vectors alone achieved an accuracy of 85.6%, which is better than 80.7% from ridge regression classifier—the best among the classical technique we tested. Additional sentiment information further increases accuracy to 86.3%. On our suicide notes dataset, the best classical technique—the Naíve Bayes Bernoulli classifier, achieves accuracy of 71.3%, while our classifier, incorporating semantic and sentiment information, exceeds that at 75% accuracy.

APA, Harvard, Vancouver, ISO, and other styles

26

Shen, Yuming, Li Liu, and Ling Shao. "Unsupervised Binary Representation Learning with Deep Variational Networks." International Journal of Computer Vision 127, no. 11-12 (2019): 1614–28. http://dx.doi.org/10.1007/s11263-019-01166-4.

Full text

APA, Harvard, Vancouver, ISO, and other styles

27

Escobar-Grisales, Daniel, Cristian David Ríos-Urrego, and Juan Rafael Orozco-Arroyave. "Deep Learning and Artificial Intelligence Applied to Model Speech and Language in Parkinson’s Disease." Diagnostics 13, no. 13 (2023): 2163. http://dx.doi.org/10.3390/diagnostics13132163.

Full text

Abstract:

Parkinson’s disease (PD) is the second most prevalent neurodegenerative disorder in the world, and it is characterized by the production of different motor and non-motor symptoms which negatively affect speech and language production. For decades, the research community has been working on methodologies to automatically model these biomarkers to detect and monitor the disease; however, although speech impairments have been widely explored, language remains underexplored despite being a valuable source of information, especially to assess cognitive impairments associated with non-motor symptoms. This study proposes the automatic assessment of PD patients using different methodologies to model speech and language biomarkers. One-dimensional and two-dimensional convolutional neural networks (CNNs), along with pre-trained models such as Wav2Vec 2.0, BERT, and BETO, were considered to classify PD patients vs. Healthy Control (HC) subjects. The first approach consisted of modeling speech and language independently. Then, the best representations from each modality were combined following early, joint, and late fusion strategies. The results show that the speech modality yielded an accuracy of up to 88%, thus outperforming all language representations, including the multi-modal approach. These results suggest that speech representations better discriminate PD patients and HC subjects than language representations. When analyzing the fusion strategies, we observed that changes in the time span of the multi-modal representation could produce a significant loss of information in the speech modality, which was likely linked to a decrease in accuracy in the multi-modal experiments. Further experiments are necessary to validate this claim with other fusion methods using different time spans.

APA, Harvard, Vancouver, ISO, and other styles

28

Bae, Kyoungman, and Youngjoong Ko. "Speech-Act Classification Using Convolutional Neural Network and Word Embedding." International Journal on Artificial Intelligence Tools 27, no. 06 (2018): 1850026. http://dx.doi.org/10.1142/s0218213018500264.

Full text

Abstract:

The application of deep learning techniques in natural language processing tasks has been increased in recent years. Many studies have used the deep learning techniques to obtain a distributed representation of features. In particular, the convolutional neural network (CNN) with the distributed representation have subsequently been shown to be effective for the natural language processing tasks. This paper presents how to apply the CNN to speech-act classification. Then we analyze the experimental results on two issues, how to solve two problems about sparse speech-acts in train data and out of vocabulary, and how to utilize the advantages of CNN in the speech-act classification. As a result, we obtain the significant improved performances when CNN is applied to the speech-act classification.

APA, Harvard, Vancouver, ISO, and other styles

29

Liu, Shuyu, Liu Yang, and Qinghua Hu. "Unsupervised Heterogeneous Transfer Learning for Partial Co-occurrence Data." International Journal on Artificial Intelligence Tools 30, no. 03 (2021): 2150012. http://dx.doi.org/10.1142/s0218213021500123.

Full text

Abstract:

Heterogeneous transfer clustering contributes to improve the performance of target domain by using the co-occurrence data from different domains without any supervision. Existing works usually use a large of complete co-occurrence data to learn the projection functions mapping heterogeneous data to a common latent feature subspace. Given that in the real-world problems, complete and abundant co-occurrence data in the form of homogeneous transfer learning between the soured domain and target domain are hard to achieve, a heterogeneous transfer clustering method for partial co-occurrence data (HTCPC) is proposed here, to perform unsupervised learning to map the partial information obtained from the source domain onto objects in the target domain. Furthermore, to maximize the useful information to improve the clustering performance in target domain, the proposed HTCPC uses the deep matrix decomposition framework to maintain the multi-layer hidden feature representation and retain the complexity of the data hierarchy by adding the approximate orthogonal constraints, which can effectively strengthen the independence and minimal redundancy. From a series of experiments conducted on four datasets [Berkeley Drosophila Genome Project (BDGP), Devanagari Handwritten Character (DHC), Columbia University Image Library (COIL), and Notting-Hill (NH)], the results show that HTCPC outperforms the peers in the following aspects: our method constructs the hierarchical structure in the multi-layer latent representations and the proposed algorithm can reduce the redundancy and extract more useful knowledge for target domain.

APA, Harvard, Vancouver, ISO, and other styles

30

Dhafar, Fakhry Hasan, and Mohammed Khidhir AbdulSattar. "Toward enhancement of deep learning techniques using fuzzy logic: a survey." International Journal of Electrical and Computer Engineering (IJECE) 13, no. 3 (2023): 3041–55. https://doi.org/10.11591/ijece.v13i3.pp3041-3055.

Full text

Abstract:

Deep learning has emerged recently as a type of artificial intelligence (AI) and machine learning (ML), it usually imitates the human way in gaining a particular knowledge type. Deep learning is considered an essential data science element, which comprises predictive modeling and statistics. Deep learning makes the processes of collecting, interpreting, and analyzing big data easier and faster. Deep neural networks are kind of ML models, where the non-linear processing units are layered for the purpose of extracting particular features from the inputs. Actually, the training process of similar networks is very expensive and it also depends on the used optimization method, hence optimal results may not be provided. The techniques of deep learning are also vulnerable to data noise. For these reasons, fuzzy systems are used to improve the performance of deep learning algorithms, especially in combination with neural networks. Fuzzy systems are used to improve the representation accuracy of deep learning models. This survey paper reviews some of the deep learning based fuzzy logic models and techniques that were presented and proposed in the previous studies, where fuzzy logic is used to improve deep learning performance. The approaches are divided into two categories based on how both of the samples are combined. Furthermore, the models' practicality in the actual world is revealed.

APA, Harvard, Vancouver, ISO, and other styles

31

Kumarasinghe, Kaushalya, Nikola Kasabov, and Denise Taylor. "Deep learning and deep knowledge representation in Spiking Neural Networks for Brain-Computer Interfaces." Neural Networks 121 (January 2020): 169–85. http://dx.doi.org/10.1016/j.neunet.2019.08.029.

Full text

APA, Harvard, Vancouver, ISO, and other styles

32

Kim, Jaehun, Julián Urbano, Cynthia C. S. Liem, and Alan Hanjalic. "One deep music representation to rule them all? A comparative analysis of different representation learning strategies." Neural Computing and Applications 32, no. 4 (2019): 1067–93. http://dx.doi.org/10.1007/s00521-019-04076-1.

Full text

APA, Harvard, Vancouver, ISO, and other styles

33

Elmadany, Nour Eldin, Yifeng He, and Ling Guan. "Improving Action Recognition via Temporal and Complementary Learning." ACM Transactions on Intelligent Systems and Technology 12, no. 3 (2021): 1–24. http://dx.doi.org/10.1145/3447686.

Full text

Abstract:

In this article, we study the problem of video-based action recognition. We improve the action recognition performance by finding an effective temporal and appearance representation. For capturing the temporal representation, we introduce two temporal learning techniques for improving long-term temporal information modeling, specifically Temporal Relational Network and Temporal Second-Order Pooling-based Network. Moreover, we harness the representation using complementary learning techniques, specifically Global-Local Network and Fuse-Inception Network. Performance evaluation on three datasets (UCF101, HMDB-51, and Mini-Kinetics-200) demonstrated the superiority of the proposed framework compared to the 2D Deep ConvNets-based state-of-the-art techniques.

APA, Harvard, Vancouver, ISO, and other styles

34

Liu, Li, Wanli Ouyang, Xiaogang Wang, et al. "Deep Learning for Generic Object Detection: A Survey." International Journal of Computer Vision 128, no. 2 (2019): 261–318. http://dx.doi.org/10.1007/s11263-019-01247-4.

Full text

Abstract:

Abstract Object detection, one of the most fundamental and challenging problems in computer vision, seeks to locate object instances from a large number of predefined categories in natural images. Deep learning techniques have emerged as a powerful strategy for learning feature representations directly from data and have led to remarkable breakthroughs in the field of generic object detection. Given this period of rapid evolution, the goal of this paper is to provide a comprehensive survey of the recent achievements in this field brought about by deep learning techniques. More than 300 research contributions are included in this survey, covering many aspects of generic object detection: detection frameworks, object feature representation, object proposal generation, context modeling, training strategies, and evaluation metrics. We finish the survey by identifying promising directions for future research.

APA, Harvard, Vancouver, ISO, and other styles

35

Panesar, Kulvinder. "Conversational artificial intelligence - demystifying statistical vs linguistic NLP solutions." Journal of Computer-Assisted Linguistic Research 4, no. 1 (2020): 47. http://dx.doi.org/10.4995/jclr.2020.12932.

Full text

Abstract:

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.

APA, Harvard, Vancouver, ISO, and other styles

36

Aman, Shukla, and Kumar Prajapati Jeetendra. "Role of Artificial Intelligence in Drug Discovery." International Journal of Trends in Emerging Research and Development 1, no. 1 (2023): 329–34. https://doi.org/10.5281/zenodo.14611183.

Full text

Abstract:

Traditional drug discovery methods, such as synthesis operations, validations, and testing in a wet laboratory, are time-consuming and expensive. The use of artificial intelligence (AI) methods in the pharmaceutical industry has been transformed by recent developments in the field. Artificial intelligence methods, when coupled with easily available data resources, are altering the course of medication development. For different phases of drug development, a number of AI-based models have been created in the last few decades. By supplementing traditional trials, these models have hastened the process of drug discovery. Molecular representation techniques are used to transform data into representations that computers can understand. We began by outlining the most popular drug discovery data sites, including ChEMBL and DrugBank. At the same time, we compiled a list of all the algorithms that went into creating AI models for medication development. We then moved on to talk about how artificial intelligence (AI) methods may be used in pharmaceutical research to forecast things like a drug's physicochemical properties, bioactivity, and toxicity. In addition, we presented the AI-powered models for creating new drugs, predicting their structures and interactions with targets, and determining their binding affinities. We went on to mention AI's cutting-edge uses in nanomedicine design and drug synergism/antagonism prediction. Lastly, we covered the benefits, drawbacks, and potential future directions of artificial intelligence in the pharmaceutical industry.

APA, Harvard, Vancouver, ISO, and other styles

37

Sheshmani, Artan, and Yi-Zhuang You. "Categorical representation learning: morphism is all you need." Machine Learning: Science and Technology 3, no. 1 (2021): 015016. http://dx.doi.org/10.1088/2632-2153/ac2c5d.

Full text

Abstract:

Abstract We provide a construction for categorical representation learning and introduce the foundations of ‘categorifier’. The central theme in representation learning is the idea of everything to vector. Every object in a dataset S can be represented as a vector in R n by an encoding map E : O b j ( S ) → R n . More importantly, every morphism can be represented as a matrix E : H o m ( S ) → R n n . The encoding map E is generally modeled by a deep neural network. The goal of representation learning is to design appropriate tasks on the dataset to train the encoding map (assuming that an encoding is optimal if it universally optimizes the performance on various tasks). However, the latter is still a set-theoretic approach. The goal of the current article is to promote the representation learning to a new level via a category-theoretic approach. As a proof of concept, we provide an example of a text translator equipped with our technology, showing that our categorical learning model outperforms the current deep learning models by 17 times. The content of the current article is part of a US provisional patent application filed by QGNai, Inc.

APA, Harvard, Vancouver, ISO, and other styles

38

Makris, Christos, and Michael Angelos Simos. "OTNEL: A Distributed Online Deep Learning Semantic Annotation Methodology." Big Data and Cognitive Computing 4, no. 4 (2020): 31. http://dx.doi.org/10.3390/bdcc4040031.

Full text

Abstract:

Semantic representation of unstructured text is crucial in modern artificial intelligence and information retrieval applications. The semantic information extraction process from an unstructured text fragment to a corresponding representation from a concept ontology is known as named entity disambiguation. In this work, we introduce a distributed, supervised deep learning methodology employing a long short-term memory-based deep learning architecture model for entity linking with Wikipedia. In the context of a frequently changing online world, we introduce and study the domain of online training named entity disambiguation, featuring on-the-fly adaptation to underlying knowledge changes. Our novel methodology evaluates polysemous anchor mentions with sense compatibility based on thematic segmentation of the Wikipedia knowledge graph representation. We aim at both robust performance and high entity-linking accuracy results. The introduced modeling process efficiently addresses conceptualization, formalization, and computational challenges for the online training entity-linking task. The novel online training concept can be exploited for wider adoption, as it is considerably beneficial for targeted topic, online global context consensus for entity disambiguation.

APA, Harvard, Vancouver, ISO, and other styles

39

Zhu, Zhuotun, Xinggang Wang, Song Bai, Cong Yao, and Xiang Bai. "Deep Learning Representation using Autoencoder for 3D Shape Retrieval." Neurocomputing 204 (September 2016): 41–50. http://dx.doi.org/10.1016/j.neucom.2015.08.127.

Full text

APA, Harvard, Vancouver, ISO, and other styles

40

Jamatia, Anupam, Steve Durairaj Swamy, Björn Gambäck, Amitava Das, and Swapan Debbarma. "Deep Learning Based Sentiment Analysis in a Code-Mixed English-Hindi and English-Bengali Social Media Corpus." International Journal on Artificial Intelligence Tools 29, no. 05 (2020): 2050014. http://dx.doi.org/10.1142/s0218213020500141.

Full text

Abstract:

Sentiment analysis is a circumstantial analysis of text, identifying the social sentiment to better understand the source material. The article addresses sentiment analysis of an English-Hindi and English-Bengali code-mixed textual corpus collected from social media. Code-mixing is an amalgamation of multiple languages, which previously mainly was associated with spoken language. However, social media users also deploy it to communicate in ways that tend to be somewhat casual. The coarse nature of social media text poses challenges for many language processing applications. Here, the focus is on the low predictive nature of traditional machine learners when compared to Deep Learning counterparts, including the contextual language representation model BERT (Bidirectional Encoder Representations from Transformers), on the task of extracting user sentiment from code-mixed texts. Three deep learners (a BiLSTM CNN, a Double BiLSTM and an Attention-based model) attained accuracy 20–60% greater than traditional approaches on code-mixed data, and were for comparison also tested on monolingual English data.

APA, Harvard, Vancouver, ISO, and other styles

41

Mishra, Ranjan Kumar, G. Y. Sandesh Reddy, and Himanshu Pathak. "The Understanding of Deep Learning: A Comprehensive Review." Mathematical Problems in Engineering 2021 (April 5, 2021): 1–15. http://dx.doi.org/10.1155/2021/5548884.

Full text

Abstract:

Deep learning is a computer-based modeling approach, which is made up of many processing layers that are used to understand the representation of data with several levels of abstraction. This review paper presents the state of the art in deep learning to highlight the major challenges and contributions in computer vision. This work mainly gives an overview of the current understanding of deep learning and their approaches in solving traditional artificial intelligence problems. These computational models enhanced its application in object detection, visual object recognition, speech recognition, face recognition, vision for driverless cars, virtual assistants, and many other fields such as genomics and drug discovery. Finally, this paper also showcases the current developments and challenges in training deep neural network.

APA, Harvard, Vancouver, ISO, and other styles

42

Asai, Masataro, Hiroshi Kajino, Alex Fukunaga, and Christian Muise. "Classical Planning in Deep Latent Space." Journal of Artificial Intelligence Research 74 (August 9, 2022): 1599–686. http://dx.doi.org/10.1613/jair.1.13768.

Full text

Abstract:

Current domain-independent, classical planners require symbolic models of the problem domain and instance as input, resulting in a knowledge acquisition bottleneck. Meanwhile, although deep learning has achieved significant success in many fields, the knowledge is encoded in a subsymbolic representation which is incompatible with symbolic systems such as planners. We propose Latplan, an unsupervised architecture combining deep learning and classical planning. Given only an unlabeled set of image pairs showing a subset of transitions allowed in the environment (training inputs), Latplan learns a complete propositional PDDL action model of the environment. Later, when a pair of images representing the initial and the goal states (planning inputs) is given, Latplan finds a plan to the goal state in a symbolic latent space and returns a visualized plan execution. We evaluate Latplan using image-based versions of 6 planning domains: 8-puzzle, 15-Puzzle, Blocksworld, Sokoban and Two variations of LightsOut.

APA, Harvard, Vancouver, ISO, and other styles

43

Mehrkanoon, Siamak. "Deep shared representation learning for weather elements forecasting." Knowledge-Based Systems 179 (September 2019): 120–28. http://dx.doi.org/10.1016/j.knosys.2019.05.009.

Full text

APA, Harvard, Vancouver, ISO, and other styles

44

Hermawan, Arya Tandy, Ilham Ari Elbaith Zaeni, Aji Prasetya Wibawa, Gunawan Gunawan, William Hartanto Hendrawan, and Yosi Kristian. "A Multi Representation Deep Learning Approach for Epileptic Seizure Detection." Journal of Robotics and Control (JRC) 5, no. 1 (2024): 187–204. http://dx.doi.org/10.18196/jrc.v5i1.20870.

Full text

Abstract:

Epileptic seizures, unpredictable in nature and potentially dangerous during activities like driving, pose significant risks to individual and public safety. Traditional diagnostic methods, which involve labour-intensive manual feature extraction from Electroencephalography (EEG) data, are being supplanted by automated deep learning frameworks. This paper introduces an automated epileptic seizure detection framework utilizing deep learning to bypass manual feature extraction. Our framework incorporates detailed pre-processing techniques: normalization via L2 normalization, filtering with an 80 Hz and 0,5 Hz Butterworth low-pass and high-pass filter, and a 50 Hz IIR Notch filter, channel selection based on standard deviation calculations and Mutual Information algorithm, and frequency domain transformation using FFT or STFT with Hann windows and 50% hop. We evaluated on two datasets: the first comprising 4 canines and 8 patients with 2.299 ictal, 23.445 interictal, and 32.915 test data, 400-5000Hz sampling rate across 16-72 channels; the second dataset, intended for testing, 733 icatal, 4.314 interictal, and 1908 test data, each 10 minutes long, recorded at 400Hz across 16 channels. Three deep learning architectures were assessed: CNN, LSTM, and a hybrid CNN-LSTM model-stems from their demonstrated efficacy in handling the complex nature of EEG data. Each model offers unique strengths, with the CNN excelling in spatial feature extraction, LSTM in temporal dynamics, and the hybrid model combining these advantages. The CNN model, comprising 31 layers, yielded highest accuracy, achieving 91% on the first dataset (precision 92%, recall 91%, F1-score 91%) and 82% on the second dataset using a 30-second threshold. This threshold was chosen for its clinical relevance. The research advances epileptic seizure detection using deep learning, indicating a promising direction for future medical technology. Future work will focus on expanding dataset diversity and refining methodologies to build upon these foundational results.

APA, Harvard, Vancouver, ISO, and other styles

45

Int., J. Electr. Eng. And Sustain. "Artificial Intelligence in Computer Science." INT. J. ELECTR. ENG. AND SUSTAIN. 2, no. 2 (2024): 01–21. https://doi.org/10.5281/zenodo.13836932.

Full text

Abstract:

Artificial Intelligence (AI) has emerged as a cornerstone of modern computer science, exerting a profound influence on diverse sectors of society. This article offers a comprehensive overview of the evolution and impact of AI in computer science. Beginning with its historical roots and development, the article traces AI's trajectory from its inception to its current state of advancement. Moreover, the article elucidates the techniques of AI in computer science, offering illuminating insights into a spectrum of methodologies including machine learning, deep learning, natural language processing, computer vision, knowledge representation and reasoning, recommender systems, and optimization techniques. In this context, the article explores the current applications of AI across various sectors, including engineering, medical fields, technology, military affairs, economy, education, entertainment, transportation, emphasizing its role in enhancing efficiency, productivity, and decision-making. In doing so, the article delves into the potential future impact of AI, envisioning a world where AI-powered technologies continue to revolutionize human-computer interaction, automation, and artificial general intelligence. To sum up, the article underscores the pivotal role of AI in shaping the future of computer science and society at large, advocating for continued research, development, and ethical stewardship of AI technologies.

APA, Harvard, Vancouver, ISO, and other styles

46

Sharma, Yasha. "Research Paper on Face Recognition using Artificial Intelligence." INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 09, no. 04 (2025): 1–9. https://doi.org/10.55041/ijsrem45987.

Full text

Abstract:

Abstract: The review paper traces the development of face recognition from initial approaches to current deep learning techniques (Hasan et al., 2021; Sáez-Trigueros et al., 2018). The earliest methods employed distinct features using SIFT and LBP (Balaban, 2015), but they lacked adequate solutions for complex situations. Statistical subspace methods improved the representation of faces when implemented. Deep Face systems initiated a transformative change in the field by achieving human-level performance through the extensive use of diverse datasets (Taigman et al., 2014). Research continues to develop robust face recognition systems that address ethical concerns regarding bias and privacy, as well as fairness, to create more acceptable solutions. Keywords: Face recognition; Illumination; partial occlusion; pose invariance.

APA, Harvard, Vancouver, ISO, and other styles

47

Garcia-Gasulla, Dario, Ferran Parés, Armand Vilalta, et al. "On the Behavior of Convolutional Nets for Feature Extraction." Journal of Artificial Intelligence Research 61 (March 20, 2018): 563–92. http://dx.doi.org/10.1613/jair.5756.

Full text

Abstract:

Deep neural networks are representation learning techniques. During training, a deep net is capable of generating a descriptive language of unprecedented size and detail in machine learning. Extracting the descriptive language coded within a trained CNN model (in the case of image data), and reusing it for other purposes is a field of interest, as it provides access to the visual descriptors previously learnt by the CNN after processing millions of images, without requiring an expensive training phase. Contributions to this field (commonly known as feature representation transfer or transfer learning) have been purely empirical so far, extracting all CNN features from a single layer close to the output and testing their performance by feeding them to a classifier. This approach has provided consistent results, although its relevance is limited to classification tasks. In a completely different approach, in this paper we statistically measure the discriminative power of every single feature found within a deep CNN, when used for characterizing every class of 11 datasets. We seek to provide new insights into the behavior of CNN features, particularly the ones from convolutional layers, as this can be relevant for their application to knowledge representation and reasoning. Our results confirm that low and middle level features may behave differently to high level features, but only under certain conditions. We find that all CNN features can be used for knowledge representation purposes both by their presence or by their absence, doubling the information a single CNN feature may provide. We also study how much noise these features may include, and propose a thresholding approach to discard most of it. All these insights have a direct application to the generation of CNN embedding spaces.

APA, Harvard, Vancouver, ISO, and other styles

48

Hitzler, Pascal, Aaron Eberhart, Monireh Ebrahimi, Md Kamruzzaman Sarker, and Lu Zhou. "Neuro-Symbolic Approaches in Artificial Intelligence." National Science Review, March 4, 2022. http://dx.doi.org/10.1093/nsr/nwac035.

Full text

Abstract:

Abstract Neuro-Symbolic Artificial Intelligence refers to a field of research and applications that combines machine learning methods based on artificial neural networks, such as deep learning, with symbolic approaches to computing and Artificial Intelligence (AI), as can be found for example in the AI subfield of Knowledge Representation and Reasoning. Neuro-Symbolic AI has a long history, however it remained a rather niche topic until recently, when landmark advances in machine learning – prompted by deep learning – caused a significant rise in interest and research activity in combining neural and symbolic methods. In this overview, we provide a rough guide to key research directions, and literature pointers for anybody interested in learning more about the field.

APA, Harvard, Vancouver, ISO, and other styles

49

Zhang, Hao, Dan Xu, Gaifang Luo, and Kangjian He. "Learning multi-level representations for affective image recognition." Neural Computing and Applications, April 22, 2022. http://dx.doi.org/10.1007/s00521-022-07139-y.

Full text

Abstract:

AbstractImages can convey intense affective experiences and affect people on an affective level. With the prevalence of online pictures and videos, evaluating emotions from visual content has attracted considerable attention. Affective image recognition aims to classify the emotions conveyed by digital images automatically. The existing studies using manual features or deep networks mainly focus on low-level visual features or high-level semantic representation without considering all factors. To better understand how deep networks are working for affective recognition tasks, we investigate the convolutional features by visualization them in this work. Our research shows that the hierarchical CNN model mainly relies on deep semantic information while ignoring the shallow visual details, which are essential to evoke emotions. To form a more general and discriminative representation, we propose a multi-level hybrid model that learns and integrates the deep semantics and shallow visual representations for sentiment classification. In addition, this study shows that class imbalance would affect performance as the main category of the affective dataset will overwhelm training and degenerate the deep networks. Therefore, a new loss function is introduced to optimize the deep affective model. Experimental results on several affective image recognition datasets show that our model outperforms various existing studies. The source code is publicly available.

APA, Harvard, Vancouver, ISO, and other styles

50

Fazi, M. Beatrice. "Beyond Human: Deep Learning, Explainability and Representation." Theory, Culture & Society, November 27, 2020, 026327642096638. http://dx.doi.org/10.1177/0263276420966386.

Full text

Abstract:

This article addresses computational procedures that are no longer constrained by human modes of representation and considers how these procedures could be philosophically understood in terms of ‘algorithmic thought’. Research in deep learning is its case study. This artificial intelligence (AI) technique operates in computational ways that are often opaque. Such a black-box character demands rethinking the abstractive operations of deep learning. The article does so by entering debates about explainability in AI and assessing how technoscience and technoculture tackle the possibility to ‘re-present’ the algorithmic procedures of feature extraction and feature learning to the human mind. The article thus mobilises the notion of incommensurability (originally developed in the philosophy of science) to address explainability as a communicational and representational issue, which challenges phenomenological and existential modes of comparison between human and algorithmic ‘thinking’ operations.

APA, Harvard, Vancouver, ISO, and other styles

Journal articles on the topic 'Artificial Intelligence; Deep learning; Representation learning'

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles