Academic literature on the topic 'Deep generative modeling'
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 'Deep generative modeling.'
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 "Deep generative modeling"
1
Blaschke, Thomas, and Jürgen Bajorath. "Compound dataset and custom code for deep generative multi-target compound design." Future Science OA 7, no. 6 (2021): FSO715. http://dx.doi.org/10.2144/fsoa-2021-0033.
Full textAbstract:
Aim: Generating a data and software infrastructure for evaluating multi-target compound (MT-CPD) design via deep generative modeling. Methodology: The REINVENT 2.0 approach for generative modeling was extended for MT-CPD design and a large benchmark data set was curated. Exemplary results & data: Proof-of-concept for deep generative MT-CPD design was established. Custom code and the benchmark set comprising 2809 MT-CPDs, 61,928 single-target and 295,395 inactive compounds from biological screens are made freely available. Limitations & next steps: MT-CPD design via deep learning is still at its conceptual stages. It will be required to demonstrate experimental impact. The data and software we provide enable further investigation of MT-CPD design and generation of candidate molecules for experimental programs.
2
Joshi, Ameya, Minsu Cho, Viraj Shah, et al. "InvNet: Encoding Geometric and Statistical Invariances in Deep Generative Models." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 04 (2020): 4377–84. http://dx.doi.org/10.1609/aaai.v34i04.5863.
Full textAbstract:
Generative Adversarial Networks (GANs), while widely successful in modeling complex data distributions, have not yet been sufficiently leveraged in scientific computing and design. Reasons for this include the lack of flexibility of GANs to represent discrete-valued image data, as well as the lack of control over physical properties of generated samples. We propose a new conditional generative modeling approach (InvNet) that efficiently enables modeling discrete-valued images, while allowing control over their parameterized geometric and statistical properties. We evaluate our approach on several synthetic and real world problems: navigating manifolds of geometric shapes with desired sizes; generation of binary two-phase materials; and the (challenging) problem of generating multi-orientation polycrystalline microstructures.
3
Lai, Peter, and Feruza Amirkulova. "Acoustic metamaterial design using Conditional Wasserstein Generative Adversarial Networks." Journal of the Acoustical Society of America 151, no. 4 (2022): A253. http://dx.doi.org/10.1121/10.0011234.
Full textAbstract:
This talk presents a method for generating planar configurations of scatterers with a reduced total scattering cross section (TSCS) by means of generative modeling and deep learning. The TSCS minimization via repeated forward modeling techniques, trial-error methods, and traditional optimization methods requires considerable computer resources and time. However, similar or better results can be achieved more efficiently by training a deep learning model to generate such optimized configurations producing low scattering effect. In this work, the Conditional Wasserstein Generative Adversarial Networks (cWGAN) is combined with Convolutional Neural Networks (CNN) to create the generative modeling architecture [1]. The generative model is implemented with a conditional proponent to allow the TSCS targeted design generation and is enhanced with the coordinate convolution (CordConv) layer to improve the model’s spatial recognition of cylinder configurations. The cWGAN model [1] is capable of generating images of 2D configurations of scatterers that exhibit low scattering. The method is demonstrated by giving examples of generating 2-cylinder and 4-cylinder planar configurations with minimal TSCS. [1]. P. Lai, F. Amirkulova, and P. Gerstoft. “Conditional Wasserstein generative adversarial networks applied to acoustic metamaterial design,” J. Acoust. Soc. Am. 150(6), 4362–4374 (2021).
4
Komanduri, Aneesh. "Toward Causal Generative Modeling: From Representation to Generation." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 28 (2025): 29275–76. https://doi.org/10.1609/aaai.v39i28.35215.
Full textAbstract:
Deep learning has given rise to the field of representation learning, which aims to automatically extract rich semantics from data. However, there have been several challenges in the generalization capabilities of deep learning models. Recent works have highlighted beneficial properties of causal models that are desirable for learning robust models under distribution shifts. Thus, there has been a growing interest in causal representation learning for achieving generalizability in tasks involving reasoning and planning. The goal of my dissertation is to develop theoretical intuitions and practical algorithms that uncover the nature of causal representations and their applications. In my work, I focus on causal generative modeling with an emphasis on either representation or generation. For representation learning, I investigate the disentanglement of causal representations through the lens of independent causal mechanisms. For generation tasks, I develop algorithms for counterfactual generation under weak supervision settings by leveraging recent advances in generative modeling. The proposed approaches have been empirically shown to be effective in achieving disentanglement and generating counterfactuals.
5
Strokach, Alexey, and Philip M. Kim. "Deep generative modeling for protein design." Current Opinion in Structural Biology 72 (February 2022): 226–36. http://dx.doi.org/10.1016/j.sbi.2021.11.008.
Full text
6
Tomczak, Jakub M. "Deep Generative Modeling: From Probabilistic Framework to Generative AI." Entropy 27, no. 3 (2025): 238. https://doi.org/10.3390/e27030238.
Full text
7
Lopez, Romain, Jeffrey Regier, Michael B. Cole, Michael I. Jordan, and Nir Yosef. "Deep generative modeling for single-cell transcriptomics." Nature Methods 15, no. 12 (2018): 1053–58. http://dx.doi.org/10.1038/s41592-018-0229-2.
Full text
8
Lee, Ung-Gi, Sang-Hee Kang, Jong-Chan Lee, Seo-Yeon Choi, Ukmyung Choi, and Cheol-Il Lim. "Development of Deep Learning-based Art Learning Support Tool: Using Generative Modeling." Korean Association for Educational Information and Media 26, no. 1 (2020): 207–36. http://dx.doi.org/10.15833/kafeiam.26.1.207.
Full text
9
Behnia, Farnaz, Dominik Karbowski, and Vadim Sokolov. "Deep generative models for vehicle speed trajectories." Applied Stochastic Models in Business and Industry 39, no. 5 (2023): 701–19. http://dx.doi.org/10.1002/asmb.2816.
Full textAbstract:
AbstractGenerating realistic vehicle speed trajectories is a crucial component in evaluating vehicle fuel economy and in predictive control of self‐driving cars. Traditional generative models rely on Markov chain methods and can produce accurate synthetic trajectories but are subject to the curse of dimensionality. They do not allow to include conditional input variables into the generation process. In this paper, we show how extensions to deep generative models allow accurate and scalable generation. Proposed architectures involve recurrent and feed‐forward layers and are trained using adversarial techniques. Our models are shown to perform well on generating vehicle trajectories using a model trained on GPS data from Chicago metropolitan area.
10
Janson, Giacomo, and Michael Feig. "Transferable deep generative modeling of intrinsically disordered protein conformations." PLOS Computational Biology 20, no. 5 (2024): e1012144. http://dx.doi.org/10.1371/journal.pcbi.1012144.
Full textAbstract:
Intrinsically disordered proteins have dynamic structures through which they play key biological roles. The elucidation of their conformational ensembles is a challenging problem requiring an integrated use of computational and experimental methods. Molecular simulations are a valuable computational strategy for constructing structural ensembles of disordered proteins but are highly resource-intensive. Recently, machine learning approaches based on deep generative models that learn from simulation data have emerged as an efficient alternative for generating structural ensembles. However, such methods currently suffer from limited transferability when modeling sequences and conformations absent in the training data. Here, we develop a novel generative model that achieves high levels of transferability for intrinsically disordered protein ensembles. The approach, named idpSAM, is a latent diffusion model based on transformer neural networks. It combines an autoencoder to learn a representation of protein geometry and a diffusion model to sample novel conformations in the encoded space. IdpSAM was trained on a large dataset of simulations of disordered protein regions performed with the ABSINTH implicit solvent model. Thanks to the expressiveness of its neural networks and its training stability, idpSAM faithfully captures 3D structural ensembles of test sequences with no similarity in the training set. Our study also demonstrates the potential for generating full conformational ensembles from datasets with limited sampling and underscores the importance of training set size for generalization. We believe that idpSAM represents a significant progress in transferable protein ensemble modeling through machine learning.
Dissertations / Theses on the topic "Deep generative modeling"
1
Skalic, Miha 1990. "Deep learning for drug design : modeling molecular shapes." Doctoral thesis, Universitat Pompeu Fabra, 2019. http://hdl.handle.net/10803/667503.
Full textAbstract:
Designing novel drugs is a complex process which requires finding molecules in a vast chemical space that bind to a specific biomolecular target and have favorable physio-chemical properties. Machine learning methods can leverage previous data and use it for new predictions helping the processes of selection of molecule candidate without relying exclusively on experiments. Particularly, deep learning can be applied to extract complex patterns from simple representations. In this work we leverage deep learning to extract patterns from three-dimensional representations of molecules. We apply classification and regression models to predict bioactivity and binding affinity, respectively. Furthermore, we show that it is possible to predict ligand properties for a particular protein pocket. Finally, we employ deep generative modeling for compound design. Given a ligand shape we show that we can generate similar compounds, and given a protein pocket we can generate potentially binding compounds.<br>El disseny de drogues novells es un procés complex que requereix trobar les molècules adequades, entre un gran ventall de possibilitats, que siguin capaces d’unir-se a la proteïna desitjada amb unes propietats fisicoquímiques favorables. Els mètodes d’aprenentatge automàtic ens serveixen per a aprofitar dades antigues sobre les molècules i utilitzar-les per a noves prediccions, ajudant en el procés de selecció de molècules potencials sense la necessitat exclusiva d’experiments. Particularment, l’aprenentatge profund pot sera plicat per a extreure patrons complexos a partir de representacions simples. En aquesta tesi utilitzem l’aprenentatge profund per a extreure patrons a partir de representacions tridimensionals de molècules. Apliquem models de classificació i regressió per a predir la bioactivitat i l’afinitat d’unió, respectivament. A més, demostrem que podem predir les propietats dels lligands per a una cavitat proteica determinada. Finalment, utilitzem un model generatiu profund per a disseny de compostos. Donada una forma d’un lligand demostrem que podem generar compostos similars i, donada una cavitat proteica, podem generar compostos que potencialment s’hi podràn unir.
2
Chen, Tian Qi. "Deep kernel mean embeddings for generative modeling and feedforward style transfer." Thesis, University of British Columbia, 2017. http://hdl.handle.net/2429/62668.
Full textAbstract:
The generation of data has traditionally been specified using hand-crafted
algorithms. However, oftentimes the exact generative process is unknown
while only a limited number of samples are observed. One such case is
generating images that look visually similar to an exemplar image or as if
coming from a distribution of images. We look into learning the generating
process by constructing a similarity function that measures how close the
generated image is to the target image. We discuss a framework in which
the similarity function is specified by a pre-trained neural network without
fine-tuning, as is the case for neural texture synthesis, and a framework
where the similarity function is learned along with the generative process
in an adversarial setting, as is the case for generative adversarial networks.
The main point of discussion is the combined use of neural networks and
maximum mean discrepancy as a versatile similarity function. Additionally, we describe an improvement to state-of-the-art style transfer
that allows faster computations while maintaining generality of the generating
process. The proposed objective has desirable properties such as a simpler
optimization landscape, intuitive parameter tuning, and consistent frame-
by-frame performance on video. We use 80,000 natural images and 80,000
paintings to train a procedure for artistic style transfer that is efficient but
also allows arbitrary content and style images.<br>Science, Faculty of<br>Computer Science, Department of<br>Graduate
3
Brodie, Michael B. "Methods for Generative Adversarial Output Enhancement." BYU ScholarsArchive, 2020. https://scholarsarchive.byu.edu/etd/8763.
Full textAbstract:
Generative Adversarial Networks (GAN) learn to synthesize novel samples for a given data distribution. While GANs can train on diverse data of various modalities, the most successful use cases to date apply GANs to computer vision tasks. Despite significant advances in training algorithms and network architectures, GANs still struggle to consistently generate high-quality outputs after training. We present a series of papers that improve GAN output inference qualitatively and quantitatively. The first chapter, Alpha Model Domination, addresses a related subfield of Multiple Choice Learning, which -- like GANs -- aims to generate diverse sets of outputs. The next chapter, CoachGAN, introduces a real-time refinement method for the latent input space that improves inference quality for pretrained GANs. The following two chapters introduce finetuning methods for arbitrary, end-to-end differentiable GANs. The first, PuzzleGAN, proposes a self-supervised puzzle-solving task to improve global coherence in generated images. The latter, Trained Truncation Trick, improves upon a common inference heuristic by better maintaining output diversity while increasing image realism. Our final work, Two Second StyleGAN Projection, reduces the time for high-quality, image-to-latent GAN projections by two orders of magnitude. We present a wide array of results and applications of our method. We conclude with implications and directions for future work.
4
Testolin, Alberto. "Modeling cognition with generative neural networks: The case of orthographic processing." Doctoral thesis, Università degli studi di Padova, 2015. http://hdl.handle.net/11577/3424619.
Full textAbstract:
This thesis investigates the potential of generative neural networks to model cognitive processes. In contrast to many popular connectionist models, the computational framework adopted in this research work emphasizes the generative nature of cognition, suggesting that one of the primary goals of cognitive systems is to learn an internal model of the surrounding environment that can be used to infer causes and make predictions about the upcoming sensory information. In particular, we consider a powerful class of recurrent neural networks that learn probabilistic generative models from experience in a completely unsupervised way, by extracting high-order statistical structure from a set of observed variables. Notably, this type of networks can be conveniently formalized within the more general framework of probabilistic graphical models, which provides a unified language to describe both neural networks and structured Bayesian models. Moreover, recent advances allow to extend basic network architectures to build more powerful systems, which exploit multiple processing stages to perform learning and inference over hierarchical models, or which exploit delayed recurrent connections to process sequential information. We argue that these advanced network architectures constitute a promising alternative to the more traditional, feed-forward, supervised neural networks, because they more neatly capture the functional and structural organization of cortical circuits, providing a principled way to combine top-down, high-level contextual information with bottom-up, sensory evidence. We provide empirical support justifying the use of these models by studying how efficient implementations of hierarchical and temporal generative networks can extract information from large datasets containing thousands of patterns. In particular, we perform computational simulations of recognition of handwritten and printed characters belonging to different writing scripts, which are successively combined spatially or temporally in order to build more complex orthographic units such as those constituting English words.<br>In questa tesi vengono studiati alcuni processi cognitivi utilizzando recenti modelli di reti neurali generative. A differenza della maggior parte dei modelli connessionisti, l’approccio computazionale adottato in questa tesi enfatizza la natura generativa della cognizione, suggerendo che uno degli obiettivi principali dei sistemi cognitivi sia quello di apprendere un modello interno dell’ambiente circostante, che può essere usato per inferire relazioni causali ed effettuare previsioni riguardo all’informazione sensoriale in arrivo. In particolare, viene considerata una potente classe di reti neurali ricorrenti in grado di apprendere modelli generativi probabilistici dall’esperienza, estraendo informazione statistica di ordine superiore da un insieme di variabili in modo totalmente non supervisionato. Questo tipo di reti può essere formalizzato utilizzando la teoria dei modelli grafici probabilistici, che consente di descrivere con lo stesso linguaggio formale sia modelli di reti neurali che modelli Bayesiani strutturati. Inoltre, architetture di rete di base possono essere estese per creare sistemi più sofisticati, sfruttando molteplici livelli di processamento per apprendere modelli generativi gerarchici o sfruttando connessioni ricorrenti direzionate per processare informazione organizzata in sequenze. Riteniamo che queste architetture avanzate costituiscano un’alternativa promettente alle più tradizionali reti neurali supervisionate di tipo feed-forward, perché riproducono più fedelmente l’organizzazione funzionale e strutturale dei circuiti corticali, consentendo di spiegare come l’evidenza sensoriale possa essere effettivamente combinata con informazione contestuale proveniente da connessioni di feedback (“top-down”). Per giustificare l’utilizzo di questo tipo di modelli, in una serie di simulazioni studiamo nel dettaglio come implementazioni efficienti di reti generative gerarchiche e temporali possano estrarre informazione da grandi basi di dati, contenenti migliaia di esempi di training. In particolare, forniamo evidenza empirica relativa al riconoscimento di caratteri stampati e manoscritti appartenenti a diversi sistemi di scrittura, che possono in seguito essere combinati spazialmente o temporalmente per costruire unità ortografiche più complesse come quelle rappresentate dalle parole inglesi.
5
Yan, Guowei. "Interactive Modeling of Elastic Materials and Splashing Liquids." The Ohio State University, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=osu1593098802306904.
Full text
6
Sadok, Samir. "Audiovisual speech representation learning applied to emotion recognition." Electronic Thesis or Diss., CentraleSupélec, 2024. http://www.theses.fr/2024CSUP0003.
Full textAbstract:
Les émotions sont vitales dans notre quotidien, devenant un centre d'intérêt majeur de la recherche en cours. La reconnaissance automatique des émotions a suscité beaucoup d'attention en raison de ses applications étendues dans des secteurs tels que la santé, l'éducation, le divertissement et le marketing. Ce progrès dans la reconnaissance émotionnelle est essentiel pour favoriser le développement de l'intelligence artificielle centrée sur l'humain. Les systèmes de reconnaissance des émotions supervisés se sont considérablement améliorés par rapport aux approches traditionnelles d’apprentissage automatique. Cependant, cette progression rencontre des limites en raison de la complexité et de la nature ambiguë des émotions. La création de vastes ensembles de données étiquetées émotionnellement est coûteuse, chronophage et souvent impraticable. De plus, la nature subjective des émotions entraîne des ensembles de données biaisés, impactant l'applicabilité des modèles d'apprentissage dans des scénarios réels.Motivé par la manière dont les humains apprennent et conceptualisent des représentations complexes dès un jeune âge avec un minimum de supervision, cette approche démontre l'efficacité de tirer parti de l'expérience antérieure pour s'adapter à de nouvelles situations. Les modèles d'apprentissage non supervisé ou auto-supervisé s'inspirent de ce paradigme. Initialement, ils visent à établir une représentation générale à partir de données non étiquetées, semblable à l'expérience préalable fondamentale dans l'apprentissage humain. Ces représentations doivent répondre à des critères tels que l'invariance, l'interprétabilité et l'efficacité. Ensuite, ces représentations apprises sont appliquées à des tâches ultérieures avec des données étiquetées limitées, telles que la reconnaissance des émotions. Cela reflète l'assimilation de nouvelles situations dans l'apprentissage humain. Dans cette thèse, nous visons à proposer des méthodes d'apprentissage de représentations non supervisées et auto-supervisées conçues spécifiquement pour des données multimodales et séquentielles, et à explorer leurs avantages potentiels dans le contexte des tâches de reconnaissance des émotions. Les principales contributions de cette thèse comprennent :1. Le développement de modèles génératifs via l'apprentissage non supervisé ou auto-supervisé pour l'apprentissage de la représentation audiovisuelle de la parole, en intégrant une modélisation temporelle et multimodale (audiovisuelle) conjointe.2. La structuration de l'espace latent pour permettre des représentations désentrelacées, améliorant l'interprétabilité en contrôlant les facteurs latents interprétables par l'humain.3. La validation de l'efficacité de nos approches à travers des analyses qualitatives et quantitatives, en particulier sur la tâche de reconnaissance des émotions. Nos méthodes facilitent l'analyse, la transformation et la génération de signaux<br>Emotions are vital in our daily lives, becoming a primary focus of ongoing research. Automatic emotion recognition has gained considerable attention owing to its wide-ranging applications across sectors such as healthcare, education, entertainment, and marketing. This advancement in emotion recognition is pivotal for fostering the development of human-centric artificial intelligence. Supervised emotion recognition systems have significantly improved over traditional machine learning approaches. However, this progress encounters limitations due to the complexity and ambiguous nature of emotions. Acquiring extensive emotionally labeled datasets is costly, time-intensive, and often impractical.Moreover, the subjective nature of emotions results in biased datasets, impacting the learning models' applicability in real-world scenarios. Motivated by how humans learn and conceptualize complex representations from an early age with minimal supervision, this approach demonstrates the effectiveness of leveraging prior experience to adapt to new situations. Unsupervised or self-supervised learning models draw inspiration from this paradigm. Initially, they aim to establish a general representation learning from unlabeled data, akin to the foundational prior experience in human learning. These representations should adhere to criteria like invariance, interpretability, and effectiveness. Subsequently, these learned representations are applied to downstream tasks with limited labeled data, such as emotion recognition. This mirrors the assimilation of new situations in human learning. In this thesis, we aim to propose unsupervised and self-supervised representation learning methods designed explicitly for multimodal and sequential data and to explore their potential advantages in the context of emotion recognition tasks. The main contributions of this thesis encompass:1. Developing generative models via unsupervised or self-supervised learning for audiovisual speech representation learning, incorporating joint temporal and multimodal (audiovisual) modeling.2. Structuring the latent space to enable disentangled representations, enhancing interpretability by controlling human-interpretable latent factors.3. Validating the effectiveness of our approaches through both qualitative and quantitative analyses, in particular on emotion recognition task. Our methods facilitate signal analysis, transformation, and generation
7
Luc, Pauline. "Apprentissage autosupervisé de modèles prédictifs de segmentation à partir de vidéos." Thesis, Université Grenoble Alpes (ComUE), 2019. http://www.theses.fr/2019GREAM024/document.
Full textAbstract:
Les modèles prédictifs ont le potentiel de permettre le transfert des succès récents en apprentissage par renforcement à de nombreuses tâches du monde réel, en diminuant le nombre d’interactions nécessaires avec l’environnement.La tâche de prédiction vidéo a attiré un intérêt croissant de la part de la communauté ces dernières années, en tant que cas particulier d’apprentissage prédictif dont les applications en robotique et dans les systèmes de navigations sont vastes.Tandis que les trames RGB sont faciles à obtenir et contiennent beaucoup d’information, elles sont extrêmement difficile à prédire, et ne peuvent être interprétées directement par des applications en aval.C’est pourquoi nous introduisons ici une tâche nouvelle, consistant à prédire la segmentation sémantique ou d’instance de trames futures.Les espaces de descripteurs que nous considérons sont mieux adaptés à la prédiction récursive, et nous permettent de développer des modèles de segmentation prédictifs performants jusqu’à une demi-seconde dans le futur.Les prédictions sont interprétables par des applications en aval et demeurent riches en information, détaillées spatialement et faciles à obtenir, en s’appuyant sur des méthodes état de l’art de segmentation.Dans cette thèse, nous nous attachons d’abord à proposer pour la tâche de segmentation sémantique, une approche discriminative se basant sur un entrainement par réseaux antagonistes.Ensuite, nous introduisons la tâche nouvelle de prédiction de segmentation sémantique future, pour laquelle nous développons un modèle convolutionnel autoregressif.Enfin, nous étendons notre méthode à la tâche plus difficile de prédiction de segmentation d’instance future, permettant de distinguer entre différents objets.Du fait du nombre de classes variant selon les images, nous proposons un modèle prédictif dans l’espace des descripteurs d’image convolutionnels haut niveau du réseau de segmentation d’instance Mask R-CNN.Cela nous permet de produire des segmentations visuellement plaisantes en haute résolution, pour des scènes complexes comportant un grand nombre d’objets, et avec une performance satisfaisante jusqu’à une demi seconde dans le futur<br>Predictive models of the environment hold promise for allowing the transfer of recent reinforcement learning successes to many real-world contexts, by decreasing the number of interactions needed with the real world.Video prediction has been studied in recent years as a particular case of such predictive models, with broad applications in robotics and navigation systems.While RGB frames are easy to acquire and hold a lot of information, they are extremely challenging to predict, and cannot be directly interpreted by downstream applications.Here we introduce the novel tasks of predicting semantic and instance segmentation of future frames.The abstract feature spaces we consider are better suited for recursive prediction and allow us to develop models which convincingly predict segmentations up to half a second into the future.Predictions are more easily interpretable by downstream algorithms and remain rich, spatially detailed and easy to obtain, relying on state-of-the-art segmentation methods.We first focus on the task of semantic segmentation, for which we propose a discriminative approach based on adversarial training.Then, we introduce the novel task of predicting future semantic segmentation, and develop an autoregressive convolutional neural network to address it.Finally, we extend our method to the more challenging problem of predicting future instance segmentation, which additionally segments out individual objects.To deal with a varying number of output labels per image, we develop a predictive model in the space of high-level convolutional image features of the Mask R-CNN instance segmentation model.We are able to produce visually pleasing segmentations at a high resolution for complex scenes involving a large number of instances, and with convincing accuracy up to half a second ahead
8
Ionascu, Beatrice. "Modelling user interaction at scale with deep generative methods." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-239333.
Full textAbstract:
Understanding how users interact with a company's service is essential for data-driven businesses that want to better cater to their users and improve their offering. By using a generative machine learning approach it is possible to model user behaviour and generate new data to simulate or recognize and explain typical usage patterns. In this work we introduce an approach for modelling users' interaction behaviour at scale in a client-service model. We propose a novel representation of multivariate time-series data as time pictures that express temporal correlations through spatial organization. This representation shares two key properties that convolutional networks have been built to exploit and allows us to develop an approach based on deep generative models that use convolutional networks as backbone. In introducing this approach of feature learning for time-series data, we expand the application of convolutional neural networks in the multivariate time-series domain, and specifically user interaction data. We adopt a variational approach inspired by the β-VAE framework in order to learn hidden factors that define different user behaviour patterns. We explore different values for the regularization parameter β and show that it is possible to construct a model that learns a latent representation of identifiable and different user behaviours. We show on real-world data that the model generates realistic samples, that capture the true population-level statistics of the interaction behaviour data, learns different user behaviours, and provides accurate imputations of missing data.<br>Förståelse för hur användare interagerar med ett företags tjänst är essentiell för data-drivna affärsverksamheter med ambitioner om att bättre tillgodose dess användare och att förbättra deras utbud. Generativ maskininlärning möjliggör modellering av användarbeteende och genererande av ny data i syfte att simulera eller identifiera och förklara typiska användarmönster. I detta arbete introducerar vi ett tillvägagångssätt för storskalig modellering av användarinteraktion i en klientservice-modell. Vi föreslår en ny representation av multivariat tidsseriedata i form av tidsbilder vilka representerar temporala korrelationer via spatial organisering. Denna representation delar två nyckelegenskaper som faltningsnätverk har utvecklats för att exploatera, vilket tillåter oss att utveckla ett tillvägagångssätt baserat på på djupa generativa modeller som bygger på faltningsnätverk. Genom att introducera detta tillvägagångssätt för tidsseriedata expanderar vi applicering av faltningsnätverk inom domänen för multivariat tidsserie, specifikt för användarinteraktionsdata. Vi använder ett tillvägagångssätt inspirerat av ramverket β-VAE i syfte att lära modellen gömda faktorer som definierar olika användarmönster. Vi utforskar olika värden för regulariseringsparametern β och visar att det är möjligt att konstruera en modell som lär sig en latent representation av identifierbara och multipla användarbeteenden. Vi visar med verklig data att modellen genererar realistiska exempel vilka i sin tur fångar statistiken på populationsnivå hos användarinteraktionsdatan, samt lär olika användarbeteenden och bidrar med precisa imputationer av saknad data.
9
McClintick, Kyle W. "Training Data Generation Framework For Machine-Learning Based Classifiers." Digital WPI, 2018. https://digitalcommons.wpi.edu/etd-theses/1276.
Full textAbstract:
In this thesis, we propose a new framework for the generation of training data for machine learning techniques used for classification in communications applications. Machine learning-based signal classifiers do not generalize well when training data does not describe the underlying probability distribution of real signals. The simplest way to accomplish statistical similarity between training and testing data is to synthesize training data passed through a permutation of plausible forms of noise. To accomplish this, a framework is proposed that implements arbitrary channel conditions and baseband signals. A dataset generated using the framework is considered, and is shown to be appropriately sized by having $11\%$ lower entropy than state-of-the-art datasets. Furthermore, unsupervised domain adaptation can allow for powerful generalized training via deep feature transforms on unlabeled evaluation-time signals. A novel Deep Reconstruction-Classification Network (DRCN) application is introduced, which attempts to maintain near-peak signal classification accuracy despite dataset bias, or perturbations on testing data unforeseen in training. Together, feature transforms and diverse training data generated from the proposed framework, teaching a range of plausible noise, can train a deep neural net to classify signals well in many real-world scenarios despite unforeseen perturbations.
10
Fang, Zhufeng. "USING GEOSTATISTICS, PEDOTRANSFER FUNCTIONS TO GENERATE 3D SOIL AND HYDRAULIC PROPERTY DISTRIBUTIONS FOR DEEP VADOSE ZONE FLOW SIMULATIONS." Thesis, The University of Arizona, 2009. http://hdl.handle.net/10150/193439.
Full textAbstract:
We use geostatistical and pedotrasnfer functions to estimate the three-dimensional distributions of soil types and hydraulic properties in a relatively large volume of vadose zone underlying the Maricopa Agriculture Center near Phoenix, Arizona. Soil texture and bulk density data from the site are analyzed geostatistically to reveal the underlying stratigraphy as well as finer features of their three-dimensional variability in space. Such fine features are revealed by cokriging soil texture and water content measured prior to large-scale long-term infiltration experiments. Resultant estimates of soil texture and bulk density data across the site are then used as input into a pedotransfer function to produce estimates of soil hydraulic parameter (saturated and residual water content θs and θr, saturated hydraulic conductivity Ks, van Genuchten parameters αand n) distributions across the site in three dimensions. We compare these estimates with laboratory-measured values of these same hydraulic parameters and find the estimated parameters match the measured well for θs, n and Ks but not well for θr nor α, while some measured extreme values are not captured. Finally the estimated soil hydraulic parameters are put into a numerical simulator to test the reliability of the models. Resultant simulated water contents do not agree well with those observed, indicating inverse calibration is required to improve the modeling performance. The results of this research conform to a previous work by Wang et al. at 2003. Also this research covers the gaps of Wang’s work in sense of generating 3-D heterogeneous fields of soil texture and bulk density by cokriging and providing comparisons between estimated and measured soil hydraulic parameters with new field and laboratory measurements of water retentions datasets.
Books on the topic "Deep generative modeling"
1
Tomczak, Jakub M. Deep Generative Modeling. Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-030-93158-2.
Full text
2
Tomczak, Jakub M. Deep Generative Modeling. Springer International Publishing, 2024. http://dx.doi.org/10.1007/978-3-031-64087-2.
Full text
3
Ganem, Gabriel Loaiza. Advances in Deep Generative Modeling With Applications to Image Generation and Neuroscience. [publisher not identified], 2019.
Find full text
4
Yahi, Alexandre. Simulating drug responses in laboratory test time series with deep generative modeling. [publisher not identified], 2019.
Find full text
5
Tomczak, Jakub. Deep Generative Modeling. Springer International Publishing AG, 2022.
Find full text
8
Hartnett, Gavin, Raffaele Vardavas, Lawrence Baker, et al. Deep Generative Modeling in Network Science with Applications to Public Policy Research. RAND Corporation, 2020. http://dx.doi.org/10.7249/wra843-1.
Full text
9
Bongard, Josh. Modeling self and others. Oxford University Press, 2018. http://dx.doi.org/10.1093/oso/9780199674923.003.0011.
Full textAbstract:
Embodied cognition is the view that intelligence arises out of the interaction between an agent’s body and its environment. Taking such a view generates novel scientific hypotheses about biological intelligence and opportunities for advancing artificial intelligence. In this chapter we review one such set of hypotheses regarding how a robot may generate models of self, and others, and then exploit those models to recover from damage or exhibit the rudiments of social cognition. This modeling of self and others draws mainly on three concepts from neuroscience and AI: forward and inverse models in the brain, the neuronal replicator hypothesis, and the brain as a hierarchical prediction machine. The chapter concludes with future directions, including the integration of deep learning methods with embodied cognition.
Book chapters on the topic "Deep generative modeling"
1
Tomczak, Jakub M. "Hybrid Modeling." In Deep Generative Modeling. Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-93158-2_5.
Full text
2
Tomczak, Jakub M. "Hybrid Modeling." In Deep Generative Modeling. Springer International Publishing, 2024. http://dx.doi.org/10.1007/978-3-031-64087-2_6.
Full text
3
Tomczak, Jakub M. "Generative Adversarial Networks." In Deep Generative Modeling. Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-93158-2_7.
Full text
4
Tomczak, Jakub M. "Generative Adversarial Networks." In Deep Generative Modeling. Springer International Publishing, 2024. http://dx.doi.org/10.1007/978-3-031-64087-2_8.
Full text
5
Tomczak, Jakub M. "Deep Generative Modeling for Neural Compression." In Deep Generative Modeling. Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-93158-2_8.
Full text
6
Tomczak, Jakub M. "Autoregressive Models." In Deep Generative Modeling. Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-93158-2_2.
Full text
7
Tomczak, Jakub M. "Energy-Based Models." In Deep Generative Modeling. Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-93158-2_6.
Full text
8
Tomczak, Jakub M. "Flow-Based Models." In Deep Generative Modeling. Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-93158-2_3.
Full text
9
Tomczak, Jakub M. "Why Deep Generative Modeling?" In Deep Generative Modeling. Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-93158-2_1.
Full text
10
Tomczak, Jakub M. "Latent Variable Models." In Deep Generative Modeling. Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-93158-2_4.
Full textConference papers on the topic "Deep generative modeling"
1
Chelaru, Bogdan, and Catalin Onutu. "BIM APLICATIONS IN THE DESIGN OF DEEP FOUNDATIONS FOR WIND TURBINES." In SGEM International Multidisciplinary Scientific GeoConference 24. STEF92 Technology, 2024. https://doi.org/10.5593/sgem2024/6.1/s27.50.
Full textAbstract:
This paper outlines three key processes: 3D modeling based on the technical records, data mapping to objects in the Building Information Modelling (BIM) model, and data extraction from the model. Access to energy is a critical concern on the modern society, but equally important of how the energy is obtained. The methods used should be efficient enough to minimize adverse environmental impact, which holds significant importance in today�s energy production landscape. In the case of non-load-bearing subsoil, high structural loads or special requirements of the building, a deep foundation with drilled piles is required for a planned structure. The structure described in this paper is a deep foundation, utilized for onshore wind turbine design. This type of foundations can support largest wind turbine generators in operation. As the turbines are increasing in size, gravity are approaching to the limits of both their capacity and economical limit. The focus of this research is to provide an accessible and easy-to-use BIM methodology for capturing and managing information derived from the technical documentation, and evidence gathered during the construction phase. The integrated meta data covers information across written parts, drawings, in-situ, and laboratory test results, planning registers, cost registers, sustainability criteria�s identification and application and predicted performance in time of the described elements. Future endeavors will be directed towards automating the process of Building Information Modeling (BIM), by developing custom scripts designed to automatically generate elements for similar structures. The findings contribute to the advancement of BIM methodology as a key tool for guiding informed decision making for green wind farms projects.
2
Rizia, Mst Mousumi, Chenchen Xu, Jennie Roberts, et al. "Understanding the Development of Disease in Radiology Scans of the Brain through Deep Generative Modelling." In 2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). IEEE, 2024. https://doi.org/10.1109/bibm62325.2024.10822442.
Full text
3
Caccia, Lucas, Herke van Hoof, Aaron Courville, and Joelle Pineau. "Deep Generative Modeling of LiDAR Data." In 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2019. http://dx.doi.org/10.1109/iros40897.2019.8968535.
Full text
4
Davoody, Amirhossein, Ananda S. Roy, and Sivakumar P. Mudanai. "Deep Generative Model for Device Variation Modeling." In 2023 International Electron Devices Meeting (IEDM). IEEE, 2023. http://dx.doi.org/10.1109/iedm45741.2023.10413830.
Full text
5
Bianco, Michael J., Sharon Gannot, and Peter Gerstoft. "Semi-Supervised Source Localization with Deep Generative Modeling." In 2020 IEEE 30th International Workshop on Machine Learning for Signal Processing (MLSP). IEEE, 2020. http://dx.doi.org/10.1109/mlsp49062.2020.9231825.
Full text
6
Li, Zhaoyu, Son P. Nguyen, Dong Xu, and Yi Shang. "Protein Loop Modeling Using Deep Generative Adversarial Network." In 2017 IEEE 29th International Conference on Tools with Artificial Intelligence (ICTAI). IEEE, 2017. http://dx.doi.org/10.1109/ictai.2017.00166.
Full text
7
Fatir Ansari, Abdul, Jonathan Scarlett, and Harold Soh. "A Characteristic Function Approach to Deep Implicit Generative Modeling." In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2020. http://dx.doi.org/10.1109/cvpr42600.2020.00750.
Full text
8
Liu, Yiding, Kaiqi Zhao, Gao Cong, and Zhifeng Bao. "Online Anomalous Trajectory Detection with Deep Generative Sequence Modeling." In 2020 IEEE 36th International Conference on Data Engineering (ICDE). IEEE, 2020. http://dx.doi.org/10.1109/icde48307.2020.00087.
Full text
9
Ghimire, Sandesh, and Linwei Wang. "Deep Generative Modeling and Analysis of Cardiac Transmembrane Potential." In 2018 Computing in Cardiology Conference. Computing in Cardiology, 2018. http://dx.doi.org/10.22489/cinc.2018.075.
Full text
10
Dai, Mengyu, and Haibin Hang. "Manifold Matching via Deep Metric Learning for Generative Modeling." In 2021 IEEE/CVF International Conference on Computer Vision (ICCV). IEEE, 2021. http://dx.doi.org/10.1109/iccv48922.2021.00652.
Full textReports on the topic "Deep generative modeling"
1
Sadoune, Igor, Marcelin Joanis, and Andrea Lodi. Implementing a Hierarchical Deep Learning Approach for Simulating multilevel Auction Data. CIRANO, 2023. http://dx.doi.org/10.54932/lqog8430.
Full textAbstract:
We present a deep learning solution to address the challenges of simulating realistic synthetic first-price sealed-bid auction data. The complexities encountered in this type of auction data include high-cardinality discrete feature spaces and a multilevel structure arising from multiple bids associated with a single auction instance. Our methodology combines deep generative modeling (DGM) with an artificial learner that predicts the conditional bid distribution based on auction characteristics, contributing to advancements in simulation-based research. This approach lays the groundwork for creating realistic auction environments suitable for agent-based learning and modeling applications. Our contribution is twofold: we introduce a comprehensive methodology for simulating multilevel discrete auction data, and we underscore the potential ofDGMas a powerful instrument for refining simulation techniques and fostering the development of economic models grounded in generative AI.
2
Huang, Lei, Meng Song, Hui Shen, et al. Deep learning methods for omics data imputation. Engineer Research and Development Center (U.S.), 2024. http://dx.doi.org/10.21079/11681/48221.
Full textAbstract:
One common problem in omics data analysis is missing values, which can arise due to various reasons, such as poor tissue quality and insufficient sample volumes. Instead of discarding missing values and related data, imputation approaches offer an alternative means of handling missing data. However, the imputation of missing omics data is a non-trivial task. Difficulties mainly come from high dimensionality, non-linear or nonmonotonic relationships within features, technical variations introduced by sampling methods, sample heterogeneity, and the non-random missingness mechanism. Several advanced imputation methods, including deep learning-based methods, have been proposed to address these challenges. Due to its capability of modeling complex patterns and relationships in large and high-dimensional datasets, many researchers have adopted deep learning models to impute missing omics data. This review provides a comprehensive overview of the currently available deep learning-based methods for omics imputation from the perspective of deep generative model architectures such as autoencoder, variational autoencoder, generative adversarial networks, and Transformer, with an emphasis on multi-omics data imputation. In addition, this review also discusses the opportunities that deep learning brings and the challenges that it might face in this field.
3
Skyllingstad, Eric D. Next Generation Modeling for Deep Water Wave Breaking and Langmuir Circulation. Defense Technical Information Center, 2009. http://dx.doi.org/10.21236/ada498290.
Full text
4
Skyllingstad, Eric D. Next Generation Modeling for Deep Water Wave Breaking and Langmuir Circulation. Defense Technical Information Center, 2008. http://dx.doi.org/10.21236/ada534062.
Full text
5
Beaulieu, Stace E., Karen Stocks, and Leslie M. Smith. FAIR Data Training for Deep Ocean Early Career Researchers: Syllabus and slide presentations. Woods Hole Oceanographic Institution, 2024. http://dx.doi.org/10.1575/1912/67631.
Full textAbstract:
It is essential for our next generation of leaders in deep ocean observing to gain knowledge and skills in research data management, including how to make data FAIR - Findable, Accessible, Interoperable, and Reusable. This educational package was developed as a virtual workshop series for Deep Ocean Early career Researchers (DOERs) with content tailored for the Deep Ocean Observing Strategy (DOOS), an international network of deep ocean observing, mapping, exploration, and modeling programs endorsed as a UN Ocean Decade Programme. Modules step through the research data lifecycle, starting with 1 “Foundational Practices for FAIR Data,” 2 “Collaborating in the Research Data Lifecycle,” 3 “Best Practices in the Ocean Sciences,” and concluding with 4 “The “R” in FAIR data lifecycle: Reusable data.” This package includes the syllabus which shows the schedule for delivery of the workshop series as well as an overview of content and learning objectives. There are no prerequisites to participate in this course. The training was delivered in English; recordings were provided ahead of the virtual sessions and a live transcript was implemented during the sessions to improve accessibility.
6
Buesseler, Buessele, Daniele Bianchi, Fei Chai, et al. Paths forward for exploring ocean iron fertilization. Woods Hole Oceanographic Institution, 2023. http://dx.doi.org/10.1575/1912/67120.
Full textAbstract:
We need a new way of talking about global warming. UN Secretary General António Guterres underscored this when he said the “era of global boiling” has arrived. Although we have made remarkable progress on a very complex problem over the past thirty years, we have a long way to go before we can keep the global temperature increase to below 2°C relative to the pre-industrial times. Climate models suggest that this next decade is critical if we are to avert the worst consequences of climate change. The world must continue to reduce greenhouse gas emissions, and find ways to adapt and build resilience among vulnerable communities. At the same time, we need to find new ways to remove carbon dioxide from the atmosphere in order to chart a “net negative” emissions pathway. Given their large capacity for carbon storage, the oceans must be included in consideration of our multiple carbon dioxide removal (CDR) options. This report focused on ocean iron fertilization (OIF) for marine CDR. This is by no means a new scientific endeavor. Several members of ExOIS (Exploring Ocean Iron Solutions) have been studying this issue for decades, but the emergence of runaway climate impacts has motivated this group to consider a responsible path forward for marine CDR. That path needs to ensure that future choices are based upon the best science and social considerations required to reduce human suffering and counter economic and ecological losses, while limiting and even reversing the negative impacts that climate change is already having on the ocean and the rest of the planet. Prior studies have confirmed that the addition of small amounts of iron in some parts of the ocean is effective at stimulating phytoplankton growth. Through enhanced photosynthesis, carbon dioxide can not only be removed from the atmosphere but a fraction can also be transferred to durable storage in the deep sea. However, prior studies were not designed to quantify how effective this storage can be, or how wise OIF might be as a marine CDR approach. ExOIS is a consortium that was created in 2022 to consider what OIF studies are needed to answer critical questions about the potential efficiency and ecological impacts of marine CDR (http://oceaniron.org). Owing to concerns surrounding the ethics of marine CDR, ExOIS is organized around a responsible code of conduct that prioritizes activities for the collective benefit of our planet with an emphasis on open and transparent studies that include public engagement. Our goal is to establish open-source conventions for implementing OIF for marine CDR that can be assessed with appropriate monitoring, reporting, and verification (MRV) protocols, going beyond just carbon accounting, to assess ecological and other non-carbon environmental effects (eMRV). As urgent as this is, it will still take 5 to 10 years of intensive work and considerable resources to accomplish this goal. We present here a “Paths Forward’’ report that stems from a week-long workshop held at the Moss Landing Marine Laboratories in May 2023 that was attended by international experts spanning atmospheric, oceanographic, and social sciences as well as legal specialists (see inside back cover). At the workshop, we reviewed prior OIF studies, distilled the lessons learned, and proposed several paths forward over the next decade to lay the foundation for evaluating OIF for marine CDR. Our discussion very quickly resulted in a recommendation for the need to establish multiple “Ocean Iron Observatories’’ where, through observations and modeling, we would be able to assess with a high degree of certainty both the durable removal of atmospheric carbon dioxide—which we term the “centennial tonne”—and the ecological response of the ocean. In a five-year phase I period, we prioritize five major research activities: 1. Next generation field studies: Studies of long-term (durable) carbon storage will need to be longer (year or more) and larger (>10,000 km2) than past experiments, organized around existing tools and models, but with greater reliance on autonomous platforms. While prior studies suggested that ocean systems return to ambient conditions once iron infusion is stopped, this needs to be verified. We suggest that these next field experiments take place in the NE Pacific to assess the processes controlling carbon removal efficiencies, as well as the intended and unintended ecological and geochemical consequences. 2. Regional, global and field study modeling Incorporation of new observations and model intercomparisons are essential to accurately represent how iron cycling processes regulate OIF effects on marine ecosystems and carbon sequestration, to support experimental planning for large-scale MRV, and to guide decision making on marine CDR choices. 3. New forms of iron and delivery mechanisms Rigorous testing and comparison of new forms of iron and their potential delivery mechanisms is needed to optimize phytoplankton growth while minimizing the financial and carbon costs of OIF. Efficiency gains are expected to generate responses closer to those of natural OIF events. 4. Monitoring, reporting, and verification: Advances in observational technologies and platforms are needed to support the development, validation, and maintenance of models required for MRV of large-scale OIF deployment. In addition to tracking carbon storage and efficiency, prioritizing eMRV will be key to developing regulated carbon markets. 5. Governance and stakeholder engagement: Attention to social dimensions, governance, and stakeholder perceptions will be essential from the start, with particular emphasis on expanding the diversity of groups engaged in marine CDR across the globe. This feedback will be a critical component underlying future decisions about whether to proceed, or not, with OIF for marine CDR. Paramount in the plan is the need to move carefully. Our goal is to conduct these five activities in parallel to inform decisions steering the establishment of ocean iron observatories at multiple locations in phase II. When completed, this decadal plan will provide a rich knowledge base to guide decisions about if, when, where, and under what conditions OIF might be responsibly implemented for marine CDR. The consensus of our workshop and this report is that now is the time for actionable studies to begin. Quite simply, we suggest that some form of marine CDR will be essential to slow down and reverse the most severe consequences of our disrupted climate. OIF has the potential to be one of these climate mitigation strategies. We have the opportunity and obligation to invest in the knowledge necessary to ensure that we can make scientifically and ethically sound decisions for the future of our planet.