Physics – Condensed Matter – Statistical Mechanics
Scientific paper
1998-01-29
Phys.Rev.E 54 (1996) pg 4066
Physics
Condensed Matter
Statistical Mechanics
5 pages, 2 figures
Scientific paper
10.1103/PhysRevE.54.4066
The generalization properties of an attractive network of non monotonic neurons which infers concepts from samples are studied. The macroscopic dynamics for the overlap between the state of the neurons with the concepts, well as the activity of the neurons, are obtained and searched for through its numerical behavior. Complex behavior leading from fixed points to chaos through a cascade of bifurcation are found, when we increase the correlation between samples or decrease the activity of the samples and the load of concepts, or tune the threshold of fatigue of the neurons. Both the information dimension and the Liapunov exponent are given, and a phase diagram is built.
No associations
LandOfFree
Inference and Chaos by a Network of Non-monotonic Neurons 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 Inference and Chaos by a Network of Non-monotonic Neurons, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Inference and Chaos by a Network of Non-monotonic Neurons will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-413420