In this paper, Quick Learning algorithm for Multidirectional Associative Memories (MAMs) is proposed. Owing to the Quick Learning algorithm, not only the storage capacity of the MAMs can be improved, but also the recall of all training data can be guaranteed. In addition, several important characteristics of the MAMs such as the relation between the required learning epochs and the number of layers and the relation between the noise reduction effect and the number of layers are introduced.
|出版ステータス||Published - 1995 12月 1|
|イベント||Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6) - Perth, Aust|
継続期間: 1995 11月 27 → 1995 12月 1
|Other||Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6)|
|Period||95/11/27 → 95/12/1|
ASJC Scopus subject areas