Past talk · AI/ML Seminar Series
Connecting Variational Autoencoders Back to the Brain
PhD Student, Computation and Neural Systems, California Institute of Technology
- Date & time
- Monday, February 1, 2021 · 1:00 PM
- Location
- Online (live stream)
Abstract
Unsupervised machine learning has recently dramatically improved our ability to model and extract structure from data. One such approach is deep latent variable models, including variational autoencoders (VAEs), which can be traced back to the Helmholtz machine and, in turn, ideas from theoretical neuroscience. Neuroscientists have further developed these ideas into a popular theory: predictive coding. Yet the machine learning community remains largely unaware of these connections. In this talk, I discuss the links between modern deep latent variable models and predictive coding, yielding several implications for correspondences between machine learning and neuroscience, including the search for backpropagation in the brain.
About the speaker
Joe Marino is a PhD candidate in the Computation & Neural Systems program at Caltech, advised by Yisong Yue. His work focuses on improving probabilistic models and inference techniques, using neuroscience-inspired ideas, within generative modeling and reinforcement learning.