Mathematical foundations of neurocomputing
Mathematical foundations of neurocomputing
复制标题
DOI：
10.1109/5.58324
复制
发表时间：
1990-09
期刊：
影响因子：
--
通讯作者：
S. Amari
中科院分区：
文献类型：
--
作者：
S. Amari
试图建立一个数学理论，显示的内在机制，能力和各种架构的神经网络的信息处理的局限性。给出了单层神经网络的一种统计分析方法，包括联想映射和完全随机网络映射的稳定性。统计神经动力学的一个基本问题被认为是在一种方式，这是不同的自旋玻璃的方法。联想记忆模型的动态分析和神经学习的一般理论，其中学习势函数起着作用，给出。提出了先进的学习和自组织理论，涵盖反向传播及其推广以及拓扑地图和信息神经表示的形成。>
An attempt is made to establish a mathematical theory that shows the intrinsic mechanisms, capabilities, and limitations of information processing by various architectures of neural networks. A method of statistically analyzing one-layer neural networks is given, covering the stability of associative mapping and mapping by totally random networks. A fundamental problem of statistical neurodynamics is considered in a way that is different from the spin-glass approach. A dynamic analysis of associative memory models and a general theory of neural learning, in which the learning potential function plays a role, are given. An advanced theory of learning and self-organization is proposed, covering backpropagation and its generalizations as well as the formation of topological maps and neural representations of information. >