Mathematical Theory of Neural Networks
Mathematical Theory of Neural Networks
复制标题
神经网络数学理论
DOI：
10.21236/ada387318
复制
发表时间：
1994
期刊：
影响因子：
--
通讯作者：
H. Sussmann
中科院分区：
文献类型：
--
作者：
Eduardo Sontag;H. Sussmann
摘要：本报告侧重于与人工神经网络的能力、性能和局限性相关的基本理论问题。对于静态（前馈）网络，调查的主题包括最小二乘拟合，VC和其他学习维度，可表示性问题和函数逼近的误差表面的研究。对于动态（循环）网络，涵盖了处理参数识别和建模，可实现性和其他系统理论问题，理论计算能力和学习理论问题的问题。
Abstract : This report focuses on fundamental theoretical issues relevant to the capabilities, performance, and limitations of artificial neural networks. For static (feedforward) networks, subjects of investigation included the study of error surfaces for least squares fitting, VC and other learning dimensions, representability questions, and function approximation. For dynamic (recurrent) nets, covered are questions dealing with parameter identification and modeling, realizability and other systems-theoretic issues, theoretical computational capabilities, and learning-theoretic issues.