Scalable Learning and Inference in Hierarchical Models of the Neocortex

Google TechTalks January 17, 2006 Tom Dean ABSTRACT Borrowing insights from computational neuroscience, we present a class of generative models well suited to modeling perceptual processes and an algorithm for learning their parameters that promises to scale to learning very large models. The models are hierarchical, composed of multiple levels, and allow input only at the lowest level, the base of the hierarchy. Connections within a level are generally local and may or may not be directed. Connections between levels are directed and generally do not span multiple levels. The learning algorithm falls within the general family of expectation maximization algorithms. Parameter estimation proceeds level-by-level starting with components in the lowest level and moving up the hierarchy. The inference required for learning is carried out by local message passing and the arrangement of connections within the underlying networks is designed to facilitate this method of inference. Learning is unsupervised but can be easily adapted to accommodate labeled data.

» View the original video «

Google Video | January 17, 2006

Tags:. .generative. .generally. .present. .moving. .underlying