Emergence of Motion-sensitive Neurons Properties by Learning Sparse Code for Natural Moving Images

Rafal Bogacz, Todd Leen, Malcolm Brown, Thomas Dietterich, Christophe Giraud-Carrier, Volker Tresp

Research output: Chapter in Book/Report/Conference proceedingChapter in a book

Abstract

Olshausen & Field demonstrated that a learning algorithm that attempts to generate a sparse code for natural scenes develops a complete family of localised, oriented, bandpass receptive fields, similar to those of 'simple cells' in V1. This paper describes an algorithm which finds a sparse code for sequences of images that preserves information about the input. This algorithm when trained on natural video sequences develops bases representing the movement in particular directions with particular speeds, similar to the receptive fields of the movement-sensitive cells observed in cortical visual areas. Furthermore, in contrast to previous approaches to learning direction selectivity, the timing of neuronal activity encodes the phase of the movement, so the precise timing of spikes is crucially important to the information encoding.
Translated title of the contributionEmergence of Motion-sensitive Neurons Properties by Learning Sparse Code for Natural Moving Images
Original languageEnglish
Title of host publicationAdvances in Neural Information Processing Systems
PublisherMassachusetts Institute of Technology (MIT) Press
Volume13
ISBN (Print)0262122413
Publication statusPublished - 2001

Bibliographical note

Other page information: 838-844
Other identifier: 1000547

Fingerprint Dive into the research topics of 'Emergence of Motion-sensitive Neurons Properties by Learning Sparse Code for Natural Moving Images'. Together they form a unique fingerprint.

Cite this