Lytton W W
Department of Neurology and Neuroscience Training Program, Wm. S. Middleton VA Hospital, University of Wisconsin, Madison 53706-1532, USA.
J Comput Neurosci. 1998 Dec;5(4):353-64. doi: 10.1023/a:1026456411040.
Using the original McCulloch-Pitts notion of simple on and off spike coding in lieu of rate coding, an Anderson-Kohonen artificial neural network (ANN) associative memory model was ported to a neuronal network with Hodgkin-Huxley dynamics. In the ANN, the use of 0/1 (no-spike/spike) units introduced a cross-talk term that had to be compensated by introducing balanced feedforward inhibition. The resulting ANN showed good capacity and fair selectivity (rejection of unknown input vectors). Translation to the Hodgkin-Huxley model resulted in a network that was functional but not at all robust. Evaluation of the weaknesses of this network revealed that it functioned far better using spike timing, rather than spike occurrence, as the code. The algorithm requires a novel learning algorithm for feedforward inhibition that could be sought physiologically.
使用原始的麦卡洛克 - 皮茨简单的开和关脉冲编码概念来代替速率编码，一个安德森 - 科霍宁人工神经网络（ANN）联想记忆模型被移植到具有霍奇金 - 赫胥黎动力学的神经元网络中。在人工神经网络中，使用0/1（无脉冲/脉冲）单元引入了一个串扰项，必须通过引入平衡的前馈抑制来补偿。所得的人工神经网络显示出良好的容量和相当的选择性（拒绝未知输入向量）。转换到霍奇金 - 赫胥黎模型后得到的网络虽然能运行，但一点也不稳健。对该网络弱点的评估表明，使用脉冲时间而非脉冲出现作为编码时，它的运行效果要好得多。该算法需要一种用于前馈抑制的新型学习算法，这可以从生理学角度去寻找。
