Open Vesicles With Two Edges

Zhou, Xiaohua; Zhang, Xiaojun; Liu, Yuansheng; Qu, Xuemin

doi:10.1142/s0217979210055809

Cited by 1 publication

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The achieved storage capacity α can be increased to some extent if we make Δt max larger, but the search process will become more and more viscous as the solution space of the problem becomes more and more heterogeneous and complex [34]. We do not attempt to calculate the jamming point of the random walk searching processes [47].…”

Section: Resultsmentioning

confidence: 99%

Learning by random walks in the weight space of the Ising perceptron

Huang

Zhou

2010

J. Stat. Mech.

View full text Add to dashboard Cite

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 α ≈ 0.63 for pattern length N = 101 and α ≈ 0.41 for N = 1001. If in addition a relearning process is exploited, the learning performance is further improved to a storage capacity of α ≈ 0.80 for N = 101 and α ≈ 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 α of the learning task; at a fixed value of α, the width of the Hamming distance distributions decreases with N .

show abstract

Section: Resultsmentioning

confidence: 99%