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.
|ジャーナル||Proceedings of the IEEE International Conference on Systems, Man and Cybernetics|
|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 8 → 2000 10月 11
ASJC Scopus subject areas