Hebbian Crosstalk Prevents Nonlinear Unsupervised Learning
نویسندگان
چکیده
Learning is thought to occur by localized, activity-induced changes in the strength of synaptic connections between neurons. Recent work has shown that induction of change at one connection can affect changes at others ("crosstalk"). We studied the role of such crosstalk in nonlinear Hebbian learning using a neural network implementation of independent components analysis. We find that there is a sudden qualitative change in the performance of the network at a threshold crosstalk level, and discuss the implications of this for nonlinear learning from higher-order correlations in the neocortex.
منابع مشابه
A Rigorous Analysis Of Linsker's Hebbian Learning Network
Abstmct We propose a novel approach for a rigorous analysis of the nonlinear asymmetric dynamics of Linsker's unsupervised Hebbian learning network. The results provide for the Arst time comprehensive explanations of the origin of the various structured connection patterns and of the roles of the different system parameters of the model. Our theoretical predictions are corroborated by numerical...
متن کاملNonlinear Complex-Valued Extensions of Hebbian Learning: An Essay
The Hebbian paradigm is perhaps the best-known unsupervised learning theory in connectionism. It has inspired wide research activity in the artificial neural network field because it embodies some interesting properties such as locality and the capability of being applicable to the basic weight-and-sum structure of neuron models. The plain Hebbian principle, however, also presents some inherent...
متن کاملHebbian Inspecificity in the Oja Model
Recent work on Long Term Potentiation in brain slices shows that Hebb's rule is not completely synapse-specific, probably due to intersynapse diffusion of calcium or other factors. We extend the classical Oja unsupervised model of learning by a single linear neuron to include Hebbian inspecificity, by introducing an error matrix E, which expresses possible crosstalk between updating at differen...
متن کاملHebbian errors in learning: an analysis using the Oja model.
BACKGROUND Recent work on long term potentiation in brain slices shows that Hebb's rule is not completely synapse-specific, probably due to intersynapse diffusion of calcium or other factors. We previously suggested that such errors in Hebbian learning might be analogous to mutations in evolution. METHODS AND FINDINGS We examine this proposal quantitatively, extending the classical Oja unsupe...
متن کاملCompetitive Learning: What are the Circuit Limitations?
This paper examines issues relating to analog CMOS circuit implementation of the soft competitive neural learning algorithm. Simulations of a proposed implementation have been conducted based on hardware models constructed from actual measurements of 1.2 μ m CMOS analog components, primarily (nonlinear) Gilbert multipliers and associated circuits. We have used these same components in the past ...
متن کامل