Dynamical Variational Autoencoders: Introduction 2. Variational Autoencoders 3. Recurrent Neural Networks and State Space Models 4. Definition of Dynamical VAEs 5. Deep Kalman Filters 6. Kalman Variational Autoencoders 7. STOchastic Recurrent Networks 8. Variational Recurrent Neural Networks 9. Stochastic Recurrent Neural Networks 10. Recurrent Variational Autoencoders 11. Disentangled Sequential Autoencoders 12. Brief tour of other models 13. Experiments 14. Discussion Acknowledgements Appendices References

Book excerpt: Variational autoencoders (VAEs) are powerful deep generative models widely used to represent high-dimensional complex data through a low-dimensional latent space learned in an unsupervised manner. In this monograph the authors introduce and discuss a general class of models, called dynamical variational autoencoders (DVAEs), which extend VAEs to model temporal vector sequences. In doing so the authors provide: 0́Ø a formal definition of the general class of DVAEs 0́Ø a detailed and complete technical description of seven DVAE models 0́Ø a rapid overview of other DVAE models presented in the recent literature 0́Ø discussion of the recent developments in DVAEs in relation to the history and technical background of the classical models DVAEs are built on 0́Ø a quantitative benchmark of the selected DVAE models 0́Ø a discussion to put the DVAE class of models into perspective This monograph is a comprehensive review of the current state-of-the-art in DVAEs. It gives the reader an accessible summary of the technical aspects of the different DVAE models, their connections with classical models, their cross-connections, and their unification in the DVAE class in a concise, easy-to-read book. The authors have put considerable effort into unifying the terminology and notation used across the various models which all students, researchers and practitioners working in machine learning will find an invaluable resource.