Abstract

I will present a class of generative models for high-dimensional time series. The first key property of these models is that they have a distributed, or "componential" latent state, which is characterized by binary stochastic variables which interact to explain the data. The second key property of these models is the nonlinear relationship between latent state and observations, based on an undirected graphical model. A final thread running through this work is the idea of deep, hierarchical representations. This is based on the idea that undirected models can form the building-blocks of deep networks by greedy unsupervised learning, one layer at a time. This work focuses on data captured from human motion (mocap). I will demonstrate how a single model can capture the regularities of different types and styles of motion.

Joint work with Geoff Hinton and Sam Roweis

Venue, Date, and Time

Venue: Newell Simon Hall 1507

Date: Monday, Jan 26, 2009

Time: 12:00 noon