Physics – Condensed Matter – Disordered Systems and Neural Networks
Scientific paper
2010-03-04
J. Stat. Mech.: Theory Exp. P08014 (2010)
Physics
Condensed Matter
Disordered Systems and Neural Networks
12 pages, 4 figures, An extensively revised version
Scientific paper
10.1088/1742-5468/2010/08/P08014
Several variants of a stochastic local search process for constructing the synaptic weights of an Ising perceptron are studied. In this process, binary patterns are sequentially presented to the Ising perceptron and are then learned as the synaptic weight configuration is modified through a chain of single- or double-weight flips within the compatible weight configuration space of the earlier learned patterns. This process is able to reach a storage capacity of $\alpha \approx 0.63$ for pattern length N = 101 and $\alpha \approx 0.41$ for N = 1001. If in addition a relearning process is exploited, the learning performance is further improved to a storage capacity of $\alpha \approx 0.80$ for N = 101 and $\alpha \approx 0.42$ for N=1001. We found that, for a given learning task, the solutions constructed by the random walk learning process are separated by a typical Hamming distance, which decreases with the constraint density $\alpha$ of the learning task; at a fixed value of $\alpha$, the width of the Hamming distance distributions decreases with $N$.
Huang Haiping
Zhou Hai-jun
No associations
LandOfFree
Learning by random walks in the weight space of the Ising perceptron 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 Learning by random walks in the weight space of the Ising perceptron, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Learning by random walks in the weight space of the Ising perceptron will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-560027