Probabilistic Models with Deep Neural Networks
Recent advances in statistical inference have significantly expanded the toolbox of probabilistic modeling. Historically, probabilistic modeling has been constrained to very restricted model classes, where exact or approximate probabilistic inference is feasible. However, developments in variational...
| Main Authors: | , , , , |
|---|---|
| Format: | info:eu-repo/semantics/article |
| Language: | English |
| Published: |
MDPI
2021
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10835/9516 |
| _version_ | 1789406651251425280 |
|---|---|
| author | Masegosa Arredondo, Andrés Ramón Cabañas de Paz, Rafael Langseth, Helge Nielsen, Thomas Dyhre Salmerón Cerdán, Antonio |
| author_facet | Masegosa Arredondo, Andrés Ramón Cabañas de Paz, Rafael Langseth, Helge Nielsen, Thomas Dyhre Salmerón Cerdán, Antonio |
| author_sort | Masegosa Arredondo, Andrés Ramón |
| collection | DSpace |
| description | Recent advances in statistical inference have significantly expanded the toolbox of probabilistic modeling. Historically, probabilistic modeling has been constrained to very restricted model classes, where exact or approximate probabilistic inference is feasible. However, developments in variational inference, a general form of approximate probabilistic inference that originated in statistical physics, have enabled probabilistic modeling to overcome these limitations: (i) Approximate probabilistic inference is now possible over a broad class of probabilistic models containing a large number of parameters, and (ii) scalable inference methods based on stochastic gradient descent and distributed computing engines allow probabilistic modeling to be applied to massive data sets. One important practical consequence of these advances is the possibility to include deep neural networks within probabilistic models, thereby capturing complex non-linear stochastic relationships between the random variables. These advances, in conjunction with the release of novel probabilistic modeling toolboxes, have greatly expanded the scope of applications of probabilistic models, and allowed the models to take advantage of the recent strides made by the deep learning community. In this paper, we provide an overview of the main concepts, methods, and tools needed to use deep neural networks within a probabilistic modeling framework. |
| format | info:eu-repo/semantics/article |
| id | oai:repositorio.ual.es:10835-9516 |
| institution | Universidad de Cuenca |
| language | English |
| publishDate | 2021 |
| publisher | MDPI |
| record_format | dspace |
| spelling | oai:repositorio.ual.es:10835-95162023-04-12T19:39:11Z Probabilistic Models with Deep Neural Networks Masegosa Arredondo, Andrés Ramón Cabañas de Paz, Rafael Langseth, Helge Nielsen, Thomas Dyhre Salmerón Cerdán, Antonio deep probabilistic modeling variational inference neural networks latent variable models Bayesian learning Recent advances in statistical inference have significantly expanded the toolbox of probabilistic modeling. Historically, probabilistic modeling has been constrained to very restricted model classes, where exact or approximate probabilistic inference is feasible. However, developments in variational inference, a general form of approximate probabilistic inference that originated in statistical physics, have enabled probabilistic modeling to overcome these limitations: (i) Approximate probabilistic inference is now possible over a broad class of probabilistic models containing a large number of parameters, and (ii) scalable inference methods based on stochastic gradient descent and distributed computing engines allow probabilistic modeling to be applied to massive data sets. One important practical consequence of these advances is the possibility to include deep neural networks within probabilistic models, thereby capturing complex non-linear stochastic relationships between the random variables. These advances, in conjunction with the release of novel probabilistic modeling toolboxes, have greatly expanded the scope of applications of probabilistic models, and allowed the models to take advantage of the recent strides made by the deep learning community. In this paper, we provide an overview of the main concepts, methods, and tools needed to use deep neural networks within a probabilistic modeling framework. 2021-02-01T09:04:54Z 2021-02-01T09:04:54Z 2021-01-18 info:eu-repo/semantics/article 1099-4300 http://hdl.handle.net/10835/9516 en https://www.mdpi.com/1099-4300/23/1/117 Attribution-NonCommercial-NoDerivatives 4.0 Internacional http://creativecommons.org/licenses/by-nc-nd/4.0/ info:eu-repo/semantics/openAccess MDPI |
| spellingShingle | deep probabilistic modeling variational inference neural networks latent variable models Bayesian learning Masegosa Arredondo, Andrés Ramón Cabañas de Paz, Rafael Langseth, Helge Nielsen, Thomas Dyhre Salmerón Cerdán, Antonio Probabilistic Models with Deep Neural Networks |
| title | Probabilistic Models with Deep Neural Networks |
| title_full | Probabilistic Models with Deep Neural Networks |
| title_fullStr | Probabilistic Models with Deep Neural Networks |
| title_full_unstemmed | Probabilistic Models with Deep Neural Networks |
| title_short | Probabilistic Models with Deep Neural Networks |
| title_sort | probabilistic models with deep neural networks |
| topic | deep probabilistic modeling variational inference neural networks latent variable models Bayesian learning |
| url | http://hdl.handle.net/10835/9516 |
| work_keys_str_mv | AT masegosaarredondoandresramon probabilisticmodelswithdeepneuralnetworks AT cabanasdepazrafael probabilisticmodelswithdeepneuralnetworks AT langsethhelge probabilisticmodelswithdeepneuralnetworks AT nielsenthomasdyhre probabilisticmodelswithdeepneuralnetworks AT salmeroncerdanantonio probabilisticmodelswithdeepneuralnetworks |