Reduced representation by neural networks with restricted receptive fields

Authors:
Marco Idiart;Barry Berk;L. F. Abbott
Affiliations:
Center for Complex Systems, Brandeis University, Waltham, MA 02254 USA;Center for Complex Systems, Brandeis University, Waltham, MA 02254 USA;Center for Complex Systems, Brandeis University, Waltham, MA 02254 USA
Venue:
Neural Computation
Year:
1995

Citing 7
Cited 0

Self-Organization in a Perceptual Network

Computer
Introduction to the theory of neural computation

Introduction to the theory of neural computation
Theoretical considerations for the analysis of population coding in motor cortex

Neural Computation
The role of constraints in Hebbian learning

Neural Computation
Local synaptic learning rules suffice to maximize mutual information in a linear network

Neural Computation
Towards a theory of early visual processing

Neural Computation
Finding minimum entropy codes

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Model neural networks can perform dimensional reductions of input data sets using correlation-based learning rules to adjust their weights. Simple Hebbian learning rules lead to an optimal reduction at the single unit level but result in highly redundant network representations. More complex rules designed to reduce or remove this redundancy can develop optimal principal component representations, but they are not very compelling from a biological perspective. Neurons in biological networks have restricted receptive fields limiting their access to the input data space. We find that, within this restricted receptive field architecture, simple correlation-based learning rules can produce surprisingly efficient reduced representations. When noise is present, the size of the receptive fields can be optimally tuned to maximize the accuracy of reconstructions of input data from a reduced representation.