Carlson A
Max-Planck-Institut für Plasmaphysik, Garching, Federal Republic of Germany.
Biol Cybern. 1990;64(2):171-6. doi: 10.1007/BF02331347.
The Hebbian rule (Hebb 1949), coupled with an appropriate mechanism to limit the growth of synaptic weights, allows a neuron to learn to respond to the first principal component of the distribution of its input signals (Oja 1982). Rubner and Schulten (1990) have recently suggested the use of an "anti-Hebbian" rule in a network with hierarchical lateral connections. When applied to neurons with linear response functions, this model allows additional neurons to learn to respond to additional principal components (Rubner and Tavan 1989). Here we apply the model to neurons with non-linear response functions characterized by a threshold and a transition width. We propose local, unsupervised learning rules for the threshold and the transition width, and illustrate the operation of these rules with some simple examples. A network using these rules sorts the input patterns into classes, which it identifies by a binary code, with the coarser structure coded by the earlier neurons in the hierarchy.
赫布规则（赫布，1949年），再加上一种限制突触权重增长的适当机制，能使神经元学会对其输入信号分布的第一主成分做出反应（奥贾，1982年）。鲁布纳和舒尔滕（1990年）最近建议在具有分层横向连接的网络中使用“反赫布”规则。当应用于具有线性响应函数的神经元时，该模型能让其他神经元学会对其他主成分做出反应（鲁布纳和塔万，1989年）。在此，我们将该模型应用于具有以阈值和过渡宽度为特征的非线性响应函数的神经元。我们针对阈值和过渡宽度提出了局部无监督学习规则，并通过一些简单示例说明这些规则的运作情况。使用这些规则的网络将输入模式分类，通过二进制编码来识别这些类别，层次结构中较早的神经元编码较粗略的结构。
