van Ooyen A, Nienhuis B
Netherlands Institute for Brain Research, Amsterdam.
Biol Cybern. 1993;70(1):47-53. doi: 10.1007/BF00202565.
We demonstrate that equipping the neurons of Fukushima's neocognitron with the phenomenon that a neuron decreases its activity when repeatedly stimulated (adaptation) markedly improves the pattern discriminatory power of the network. By means of adaptation, circuits for extracting discriminating features develop preferentially. In the original neocognitron, in contrast, features shared by different patterns are preferentially learned, as connections required for extracting them are more frequently reinforced.
我们证明，为福岛新认知机的神经元配备一种现象，即神经元在反复受到刺激时会降低其活动（适应性），可显著提高网络的模式辨别能力。通过适应性，用于提取辨别特征的电路会优先发展。相比之下，在原始的新认知机中，不同模式共享的特征会被优先学习，因为提取这些特征所需的连接会更频繁地得到强化。
