Reinforcement learning algorithm with network extension for pulse neural network

Koichiro Takita, Yuko Osana, Masafumi Hagiwara

研究成果: Conference article査読

抄録

In this paper, we propose a new hierarchical pulse neural network and its reinforcement learning algorithm with network extension. The proposed pulse neural network has three layers, and all of the neurons are pulse neurons. This network learns relations between input pulse sequences and the desired outputs by updating connection weights and by adding neurons dynamically. We carried out the computer simulation to confirm the performance of the proposed algorithm.

本文言語English
ページ(範囲)2586-2591
ページ数6
ジャーナルProceedings of the IEEE International Conference on Systems, Man and Cybernetics
4
出版ステータスPublished - 2000 12月 1
イベント2000 IEEE International Conference on Systems, Man and Cybernetics - Nashville, TN, USA
継続期間: 2000 10月 82000 10月 11

ASJC Scopus subject areas

  • 制御およびシステム工学
  • ハードウェアとアーキテクチャ

フィンガープリント

「Reinforcement learning algorithm with network extension for pulse neural network」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル