Hebbian Crosstalk Prevents Nonlinear Unsupervised Learning

摘要

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.