A Learning Process of a Stochastic Feed-Forward Neural Network

スポンサーリンク

概要

• 論文の詳細を見る

• A positive reinforcement type learning algorithm is formulated for a stochastic feed-forward neural network by minimizing a relative entropic measure, and a learning equation similar to that of the Boltzmann machine is obtained. The learning of the network actually shows a similar result to that of the Boltzmann machine in the classification problems of AND and XOR, by numerical experiments.

• 社団法人日本物理学会の論文
• 1995-03-15

著者

• Fujiki Sumiyoshi

  Graduate School Of Information Science Tohoku University

• Fujiki Sumiyoshi

  Graduate School Of Information Sciences Tohoku University

• FUJIKI Nahomi

  Sendai National Collage of Technology

• Fujiki M.

  Sendai National Collage Of Technology

• Fujiki Sumiyoshi

  Graduate School of Information Sciences, Tohoku University

関連論文

• Learning Processes of Layered Neural Networks
• Learning Algorithms of Multilayer Neural Networks
• Monte Carlo Study of the Ferromagnetic Six-State Clock Model on the Triangular Lattice
• A Learning Process of a Stochastic Feed-Forward Neural Network

スポンサーリンク