偽記憶のない連想記憶システム : ヒステリシスニューロンと一般化逆行列モデル A Spurious-Memory Free Associative Memory System : Hysteresis Neurons and Pseudo-Inverse Matrix ModeI
The existence of spurious memories is a serious problem in associative memory systems based on recurrent neural networks. We propose an associative memory system which consists of hysteresis neurons and pseudo-inverse matrix weights, and show that it has no spurious memories. First, we show the patterns which are not included in the space spanned by the stored patterns, namely memory space, are unstable in dynamics of hysteresis neurons using the characteristics that pseudo-inverse matrix weights project the input vector onto the memory space. Next, we consider the condition under which no patterns except for the stored ones exist in the memory space.
- 日本神経回路学会誌 = The Brain & neural networks
日本神経回路学会誌 = The Brain & neural networks 3(4), 141-146, 1996-12-05
Japanese Neural Network Society