Hebbian Crosstalk Prevents Nonlinear Unsupervised Learning

Details Hebbian Crosstalk Prevents Nonlinear Unsupervised Learning Hebbian Crosstalk Prevents Nonlinear Unsupervised Learning

2008-02-21

arxiv.org/abs/0802.2967v1

Biology

Quantitative Biology

Neurons and Cognition

Scientific paper

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.

Affiliated with

Also associated with

No associations

Rating

Hebbian Crosstalk Prevents Nonlinear Unsupervised Learning does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Hebbian Crosstalk Prevents Nonlinear Unsupervised Learning, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Hebbian Crosstalk Prevents Nonlinear Unsupervised Learning will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-578305