NEOCOGNITRON - A SELF-ORGANIZING NEURAL NETWORK MODEL FOR A MECHANISM OF PATTERN-RECOGNITION UNAFFECTED BY SHIFT IN POSITION
NEOCOGNITRON - A SELF-ORGANIZING NEURAL NETWORK MODEL FOR A MECHANISM OF PATTERN-RECOGNITION UNAFFECTED BY SHIFT IN POSITION
复制标题
DOI：
10.1007/bf00344251
复制
发表时间：
1980-01-01
影响因子：
1.9
通讯作者：
FUKUSHIMA, K
中科院分区：
文献类型：
--
作者：
FUKUSHIMA, K
本文提出了一种人类视觉模式识别机制的神经网络模型。该网络是自组织的学习没有老师，并获得了识别刺激模式的基础上几何相似性（完形）的形状，而不受其位置的影响。这个网络被称为Neocognitron。在完成自组织后，网络具有类似于Hubel和Wiesel提出的视觉神经系统的层次模型的结构。该网络由一个输入层和一个级联连接的模块化结构组成，每个模块化结构由2层级联连接的单元组成。每个模块的第一层由S细胞组成，其显示出类似于简单细胞或低阶超复杂细胞的特征，第二层由C细胞组成，其类似于复杂细胞或高阶超复杂细胞。每个S细胞的传入突触都具有可塑性和可修饰性。该网络具有无监督学习的能力。自组织过程中不需要教师，教师只需要向网络的输入层反复呈现一组刺激模式。这个网络是在一台数字计算机上模拟的。在重复呈现一组刺激模式之后，每个刺激模式已经变成仅从最后一层的C细胞中的一个引出输出，并且相反地，该C细胞已经变成仅对该刺激模式选择性地响应。最后一层的C细胞对一种以上的刺激模式都没有反应。最后一层的C细胞的响应完全不受图案位置的影响。它既不受形状上的小变化的影响，也不受刺激图案大小上的小变化的影响。
A neural network model for a mechanism of human visual pattern recognition is proposed in this paper. The network is self-organized by learning without a teacher, and acquires an ability to recognize stimulus patterns based on the geometrical similarity (Gestalt) of their shapes without affected by their positions. This network is given a nickname neocognitron. After completion of self-organization, the network has a structure similar to the hierarchy model of the visual nervous system proposed by Hubel and Wiesel. The network consists of an input layer followed by a cascade connection of a number of modular structures, each of which is composed of 2 layers of cells connected in a cascade. The 1st layer of each module consists of S-cells, which show characteristics similar to simple cells or lower order hypercomplex cells, and the 2nd layer consists of C-cells similar to complex cells or higher order hypercomplex cells. The afferent synapses to each S-cell have plasticity and are modifiable. The network has an ability of unsupervised learning. A teacher is not needed during the process of self-organization, and its-only needed to present a set of stimulus patterns repeatedly to the input layer of network. The network was stimulated on a digital computer. After repetitive presentation of a set of stimulus patterns, each stimulus pattern has become to elicit an output only from 1 of the C-cells of the last layer, and conversely, this C-cell has become selectively responsive only to that stimulus pattern. None of the C-cells of the last layer responds to more than one stimulus pattern. The response of the C-cells of the last layer is not affected by the pattern''s position at all. Neither is it affected by a small change in shape nor in size of the stimulus pattern.