Learning Feature Hierarchies for Vision

This month we're very lucky to have Yann LeCun from Courant Institute of Mathematical Sciences and Center for Neural Science at NYU presenting "Learning Feature Hierarchies for Vision." Here's Yann's abstract:

Intelligent perceptual tasks such as vision and audition require the construction of good internal representations. Theoretical and empirical evidence suggest that the perceptual world is best represented by a multi-stage hierarchy in which features in successive stages are increasingly global, invariant, and abstract. An important challenge for Machine Learning is to devise "deep learning" methods than can automatically learn good feature hierarchies from labeled and unlabeled data.

A class of such methods that combine unsupervised sparse coding, and supervised refinement will be described. The methods are used to train a biologically-inspired vision architecture called convolutional network. It consists of multiple stages of filter banks, non-linear operations, and spatial pooling operations, analogous to the simple cells and complex cells in the mammalian visual cortex.

A number of applications will be shown through videos and live demos, including a category-level object recognition system that can be trained on the fly, a pedestrian detector, and system that recognizes human activities in videos, and a trainable vision system for off-road mobile robot navigation. A very fast implementation of these systems on specialized hardware will be shown. It is based on a new programmable and reconfigurable "dataflow" architecture dubbed NeuFlow.

More info on Yann here: http://yann.lecun.com (http://yann.lecun.com/)