Democratic Reinforcement: Learning via Self-Organization

Details Democratic Reinforcement: Learning via Self-Organization Democratic Reinforcement: Learning via Self-Organization

1996-01-23

arxiv.org/abs/cond-mat/9601113v1

Physics

Condensed Matter

9 pages (TeX), 3 figures supllied on request

Scientific paper

The problem of learning in the absence of external intelligence is discussed in the context of a simple model. The model consists of a set of randomly connected, or layered integrate-and fire neurons. Inputs to and outputs from the environment are connected randomly to subsets of neurons. The connections between firing neurons are strengthened or weakened according to whether the action is successful or not. The model departs from the traditional gradient-descent based approaches to learning by operating at a highly susceptible ``critical'' state, with low activity and sparse connections between firing neurons. Quantitative studies on the performance of our model in a simple association task show that by tuning our system close to this critical state we can obtain dramatic gains in performance.

Affiliated with

Also associated with

No associations

Rating

Democratic Reinforcement: Learning via Self-Organization 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 Democratic Reinforcement: Learning via Self-Organization, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Democratic Reinforcement: Learning via Self-Organization will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-591177