Approximate Inference and Deep Generative Models
Advances in deep generative models are at the forefront of deep learning research because of the promise they offer for allowing data-efficient learning, and for model-based reinforcement learning. In this talk I’ll review a few standard methods for approximate inference and introduce modern approximations which allow for efficient large-scale training of a wide variety of generative models. Finally, I’ll demonstrate several important application of these models to density estimation, missing data imputation, data compression and planning.
Date:
13 September 2017, 13:30 (Wednesday, 21st week, Trinity 2017)
Venue:
Le Gros Clark Building, off South Parks Road OX1 3QX
Venue Details:
lecture theatre
Speaker:
Dr Danilo Jimenez Rezende (Deepmind)
Organiser:
Dr Friedemann Zenke (University of Oxford)
Organiser contact email address:
friedemann.zenke@cncb.ox.ac.uk
Host:
Dr Friedemann Zenke (University of Oxford)
Part of:
Oxford Neurotheory Forum
Booking required?:
Not required
Audience:
Members of the University only
Editor:
Friedemann Zenke
