New results of Quick Learning for Bidirectional Associative Memory having high capacity
説明
Several important characteristics of Quick Learning for Bidirectional Associative Memory (QLBAM) are introduced. QLBAM uses two stage learning. In the first stage, the BAM is trained by Hebbian learning and then by Pseudo-Relaxation Learning Algorithm for BAM (PRLAB). The following features of the QLBAM are made clear: it is insensitive to correlation of training pairs; it is robust for noisy inputs; the minimum absolute value of net inputs indexes a noise margin; the memory capacity is greatly improved: the maximum capacity in our simulation is about 2.2N. >
収録刊行物
-
- Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94)
-
Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94) 2 1080-1085, 2002-12-17
IEEE