Binocular disparity encoding cells generated through an infomax based learning algorithm

Authors:
Kenji Okajima
Affiliations:
Fundamental Research Laboratories, System Device and Fundamental Research, NEC Corporation, 34 Miyukigaoka, Tsukuba, Ibaraki 305-8501 Japan
Venue:
Neural Networks
Year:
2004

Citing 6
Cited 1

Self-Organization in a Perceptual Network

Computer
The Gabor function extracts the maximum information from input local signals

Neural Networks
Two-dimensional Gabor-type receptive field as derived by mutual information maximization

Neural Networks
An Infomax-based learning rule that generates cells similar to visual cortical neurons

Neural Networks
Deriving Receptive Fields Using an Optimal Encoding Criterion

Advances in Neural Information Processing Systems 5, [NIPS Conference]
A Complex Cell–Like Receptive Field Obtained by Information Maximization

Neural Computation

Spatiotemporal receptive fields of direction selective cells self-organized by an Infomax-based learning model

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

A learning algorithm for a model binocular cell was derived according to an information maximization principle and by using a low signal-to-noise-ratio approximation. The algorithm updates cell's synaptic weights so that the information obtained from the cell's output is increased. According to the algorithm, model binocular cells were trained by using computer-generated stereo images as training data. As a result, cells tuned to various disparities were generated. Also, generated synaptic weight patterns of the cells were similar to Gabor-wavelets and receptive fields of simple cells in the visual cortex. Thus, they were orientation and spatial frequency selective as well as disparity selective. Gabor functions were used to fit the generated weight patterns. The fitting results indicated that the generated cells encode disparities in terms of phase disparity and/or position disparity. This result agrees with experimental findings by Anzai et al. [J Neurophys 82 (1999) 874] and is consistent with ICA-based theoretical results obtained [Network: Comput Neural Syst 11 (2000) 191].