Competing neural networks: Finding a strategy for the game of matching pennies

Details Competing neural networks: Finding a strategy for the game of matching pennies Competing neural networks: Finding a strategy for the game of matching pennies

2000-02-22

arxiv.org/abs/cond-mat/0002335v1

Physics

Condensed Matter

Disordered Systems and Neural Networks

9 pages, 5 figures

Scientific paper

10.1103/PhysRevE.62.4049

The ability of a deterministic, plastic system to learn to imitate stochastic
behavior is analyzed. Two neural networks -actually, two perceptrons- are put
to play a zero-sum game one against the other. The competition, by acting as a
kind of mutually supervised learning, drives the networks to produce an
approximation to the optimal strategy, that is to say, a random signal.

Affiliated with

Also associated with

No associations

Rating

Competing neural networks: Finding a strategy for the game of matching pennies 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 Competing neural networks: Finding a strategy for the game of matching pennies, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Competing neural networks: Finding a strategy for the game of matching pennies will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-557755