SELF-ORGANIZATION IN A PERCEPTUAL NETWORK
SELF-ORGANIZATION IN A PERCEPTUAL NETWORK
复制标题
DOI：
10.1109/2.36
复制
发表时间：
1988-03-01
期刊：
影响因子：
2.2
通讯作者：
LINSKER, R
中科院分区：
文献类型：
--
作者：
LINSKER, R
探索了从简单的多层网络的发展规则中出现的特征分析功能。它表明，即使是一个单一的发展细胞的分层网络表现出显着的优化性能，是密切相关的问题，统计，理论物理，自适应信号处理，人工智能知识表示的形成，和信息论。所研究的网络是基于视觉系统的。这些结果被用来推断一个信息理论的原则，可以应用到整个网络，而不是一个单一的细胞。提出的组织原则是，网络连接的发展，以这样的方式，以最大限度地提高信息量时，被保存在每个处理阶段的信号被转换，受到一定的约束。这一原则的操作说明了一些简单的情况。<>
The emergence of a feature-analyzing function from the development rules of simple, multilayered networks is explored. It is shown that even a single developing cell of a layered network exhibits a remarkable set of optimization properties that are closely related to issues in statistics, theoretical physics, adaptive signal processing, the formation of knowledge representation in artificial intelligence, and information theory. The network studied is based on the visual system. These results are used to infer an information-theoretic principle that can be applied to the network as a whole, rather than a single cell. The organizing principle proposed is that the network connections develop in such a way as to maximize the amount of information that is preserved when signals are transformed at each processing stage, subject to certain constraints. The operation of this principle is illustrated for some simple cases.<>