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: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/23/1/117 |
| _version_ | 1797410221202604032 |
|---|---|
| author | Andrés R. Masegosa Rafael Cabañas Helge Langseth Thomas D. Nielsen Antonio Salmerón |
| author_facet | Andrés R. Masegosa Rafael Cabañas Helge Langseth Thomas D. Nielsen Antonio Salmerón |
| author_sort | Andrés R. Masegosa |
| collection | DOAJ |
| 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. |
| first_indexed | 2024-03-09T04:26:44Z |
| format | Article |
| id | doaj.art-57c0bd55a4bc400e96dd46e4fd23f0b2 |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-03-09T04:26:44Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-57c0bd55a4bc400e96dd46e4fd23f0b22023-12-03T13:39:09ZengMDPI AGEntropy1099-43002021-01-0123111710.3390/e23010117Probabilistic Models with Deep Neural NetworksAndrés R. Masegosa0Rafael Cabañas1Helge Langseth2Thomas D. Nielsen3Antonio Salmerón4Department of Mathematics, Center for the Development and Transfer of Mathematical Research to Industry (CDTIME), University of Almería, 04120 Almería, SpainIstituto Dalle Molle di Studi sull’Intelligenza Artificiale (IDSIA), CH-6962 Lugano, SwitzerlandDepartment of Computer Science, Norwegian University of Science and Technology, NO-7491 Trondheim, NorwayDepartment of Computer Science, Aalborg University, DK-9220 Aalborg, DenmarkDepartment of Mathematics, Center for the Development and Transfer of Mathematical Research to Industry (CDTIME), University of Almería, 04120 Almería, SpainRecent 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.https://www.mdpi.com/1099-4300/23/1/117deep probabilistic modelingvariational inferenceneural networkslatent variable modelsBayesian learning |
| spellingShingle | Andrés R. Masegosa Rafael Cabañas Helge Langseth Thomas D. Nielsen Antonio Salmerón Probabilistic Models with Deep Neural Networks Entropy deep probabilistic modeling variational inference neural networks latent variable models Bayesian learning |
| 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 | https://www.mdpi.com/1099-4300/23/1/117 |
| work_keys_str_mv | AT andresrmasegosa probabilisticmodelswithdeepneuralnetworks AT rafaelcabanas probabilisticmodelswithdeepneuralnetworks AT helgelangseth probabilisticmodelswithdeepneuralnetworks AT thomasdnielsen probabilisticmodelswithdeepneuralnetworks AT antoniosalmeron probabilisticmodelswithdeepneuralnetworks |