arXiv · cond-mat/9906058
Dynamics of Interacting Neural Networks
Abstract
The dynamics of interacting perceptrons is solved analytically. For a directed flow of information the system runs into a state which has a higher symmetry than the topology of the model. A symmetry breaking phase transition is found with increasing learning rate. In addition it is shown that a system of interacting perceptrons which is trained on the history of its minority decisions develops a good strategy for the problem of adaptive competition known as the Bar Problem or Minority Game.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
W. Kinzel, R. Metzler, I. Kanter. 2000-03-03. Dynamics of Interacting Neural Networks. https://arxiv.org/abs/cond-mat/9906058
Cite the original work for its findings. Save a collection to share your selection of sources.