Pattern Formation of Synaptic Connections in a Generalized Hebb-Type Learning Model

スポンサーリンク

概要

• 論文の詳細を見る

• On the basis of a generalized Hebb-type learning model we discuss pattern forma-lion of synapses in neural network system. We propose a generalized Hebb-type learn-ing equation in which connection weight of synapse has an arbitrary potential func-tion. Especially much attention is paid for the case where potexatial has doc?b1e stablepoints. Conaputer simulation is performed upon this model and it is found that thisneural network model has a merit that system keeps learned patterns after inputsignals are stopped. The correspondence of our model with playsiological observa-tions is discussed.Ineural network, Hebb learning, double minimum potential, pattern formation, lf selective stabilization hypothesis, computer simulationl

• 社団法人日本物理学会の論文
• 1992-02-15

著者

• Usami Yoshiyuki

  Institute Of Physics Kanagawa University

関連論文

• Pattern Formation of Synaptic Connections in a Generalized Hebb-Type Learning Model

スポンサーリンク