A Simple Hebbian/Anti-Hebbian Network Learns the Sparse, Independent Components of Natural Images

Authors:
Michael S. Falconbridge;Robert L. Stamps;David R. Badcock
Affiliations:
School of Psychology, University of Western Australia, Nedlands WA 6009, Australia;School of Physics, University of Western Australia, Nedlands WA 6009, Australia;School of Psychology, University of Western Australia, Nedlands WA 6009, Australia
Venue:
Neural Computation
Year:
2006

Citing 4
Cited 7

What does the retina know about natural scenes?

Neural Computation
Representation and separation of signals using nonlinear PCA type learning

Neural Networks
Statistical basis of nonlinear Hebbian learning and application to clustering

Neural Networks
Derivation of the visual contrast response function by maximizing information rate

Neural Computation

Learning sensory representations with intrinsic plasticity

Neurocomputing
A sparse generative model of v1 simple cells with intrinsic plasticity

Neural Computation
Receptive field self-organization in a model of the fine structure in v1 cortical columns

Neural Computation
Spatio-temporal adaptation in the unsupervised development of networked visual neurons

IEEE Transactions on Neural Networks
Unsupervised learning of generative and discriminative weights encoding elementary image components in a predictive coding model of cortical function

Neural Computation
Learning invariance from natural images inspired by observations in the primary visual cortex

Neural Computation
Replicating receptive fields of simple and complex cells in primary visual cortex in a neuronal network model with temporal and population sparseness and reliability

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Slightly modified versions of an early Hebbian/anti-Hebbian neural network are shown to be capable of extracting the sparse, independent linear components of a prefiltered natural image set. An explanation for this capability in terms of a coupling between two hypothetical networks is presented. The simple networks presented here provide alternative, biologically plausible mechanisms for sparse, factorial coding in early primate vision.