Learning is thought to occur by localized, experience-induced changes in the strength of synaptic connections between neurons. Recent work has shown that activity-dependent changes 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 (ICA). We find that there is a sudden qualitative change in the performance of the network at a critical crosstalk level and discuss the implications of this for nonlinear learning from higher-order correlations in the neocortex.
@article{arxiv.0802.2967,
title = {Hebbian Crosstalk Prevents Nonlinear Unsupervised Learning},
author = {Kingsley J. A. Cox and Paul R. Adams},
journal= {arXiv preprint arXiv:0802.2967},
year = {2008}
}