Adaptive learning by extremal dynamics and negative feedback

Details Adaptive learning by extremal dynamics and negative feedback Adaptive learning by extremal dynamics and negative feedback

2000-09-14

arxiv.org/abs/cond-mat/0009211v1

Physics

Condensed Matter

Disordered Systems and Neural Networks

Scientific paper

10.1103/PhysRevE.63.031912

We describe a mechanism for biological learning and adaptation based on two simple principles: (I) Neuronal activity propagates only through the network's strongest synaptic connections (extremal dynamics), and (II) The strengths of active synapses are reduced if mistakes are made, otherwise no changes occur (negative feedback). The balancing of those two tendencies typically shapes a synaptic landscape with configurations which are barely stable, and therefore highly flexible. This allows for swift adaptation to new situations. Recollection of past successes is achieved by punishing synapses which have once participated in activity associated with successful outputs much less than neurons that have never been successful. Despite its simplicity, the model can readily learn to solve complicated nonlinear tasks, even in the presence of noise. In particular, the learning time for the benchmark parity problem scales algebraically with the problem size N, with an exponent $k\sim 1.4$.

Affiliated with

Also associated with

No associations

Rating

Adaptive learning by extremal dynamics and negative feedback 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 Adaptive learning by extremal dynamics and negative feedback, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Adaptive learning by extremal dynamics and negative feedback will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-566860