Some Characteristics of Higher Order Neural Networks with Decreasing Energy Functions (Special Section on Nonlinear Theory and its Applications)

スポンサーリンク

概要

• 論文の詳細を見る

• This paper describes some dynamical properties of higher order neural networks with decreasing energy functions. First, we will show that for any symmetric higher order neural network which permits only one element to transit at each step, there are only periodic sequences with the length 1.Further, it will be shown that for any higher order neural network, with decreasing energy functions, which permits all elements to transit at each step, there does not exist any periodic sequence with the length being over k + 1, where k is the order of the network. Lastly, we will give a characterization for higher order neural networks, with the order 2 and a decreasing energy function each, which permit plural elements to transit at each step and have periodic sequences only with the lengh 1.

• 社団法人電子情報通信学会の論文
• 1996-10-25

著者

• MIYAJIMA Hiromi

  the Faculty of Engineering, Kagoshima University

• Maeda Michiharu

  The Faculty Of Engineering Kagoshima University

• Yatsuki Shuji

  The Faculty Of Engineering Kagoshima University

• Miyajima Hiromi

  The Faculty Of Engineering Kagoshima University

関連論文

• An Investigation of Fuzzy Model Using AIC
• Destructive Fuzzy Modeling Using Neural Gas Network
• Competitive Learning Algorithms Founded on Adaptivity and Sensitivity Deletion Methods
• Some Characteristics of Higher Order Neural Networks with Decreasing Energy Functions (Special Section on Nonlinear Theory and its Applications)
• An Adaptive Learning and Self-Deleting Neural Network for Vector Quantization
• Adaptation Strength According to Neighborhood Ranking of Self-Organizing Neural Networks(Nonlinear Theory and Its Applications)

スポンサーリンク