Departmental Bulletin Paper 簡素な進化的アルゴリズムと ヒステリシスニューラルネットの合成

山岡, 慧

This paper presents the growing greedy search algorithm and its application to associative memories of hysteresis neural networks in which storage of desired memories are guaranteed. In the algorithm, individuals correspond to cross-connection parameters, the cost function evaluatesthe number of spurious memories, and the set of individuals can grow depending on the global best. Performing basic numerical experiments, the algorithm efficiency is investigated.Key Words : greedy search, hysteresis neural nets, associative memories

Number of accesses :  

Other information