Uttley A M
Brain Res. 1976 Jan 30;102(1):23-35. doi: 10.1016/0006-8993(76)90573-4.
A neural network theory is proposed which offers an explanation of many of the facts of classical and operant conditioning and adaptive pattern recognition. Interconnected networks of units have been studied and simulated which embody only two rules; firstly, units have inputs from pathways of variable and of fixed conductivity; secondly, the conductivity of a variable pathway is made proportional to the negative of the mutual information function between the signals at its input and output. The signal in a fixed pathway indicates whether the total input to the variable pathways is a member or not of some class. After a learning phase in which the unit, called an informon, receives such labelled inputs, it is able to predict the class of future unlabelled inputs. Such units are stable and their steady state can be calculated.
提出了一种神经网络理论，该理论对经典条件作用和操作性条件作用以及自适应模式识别中的许多事实做出了解释。已经对相互连接的单元网络进行了研究和模拟，这些网络仅体现两条规则：首先，单元具有来自可变传导率和固定传导率通路的输入；其次，可变通路的传导率与该通路输入和输出信号之间互信息函数的负值成比例。固定通路中的信号表明可变通路的总输入是否属于某一类别。在一个学习阶段之后，被称为信息子的单元接收此类带标签的输入，它就能够预测未来未带标签输入的类别。此类单元是稳定的，并且其稳态可以计算出来。
