摘要
本文提出了人工神经元群的逐层学习方法.该方法所建议的学习过程与人类个体及社会知识的增长过程较为接近,并且可以改善网络系统的泛化能力,提高系统的学习效率.本文对一些具体问题进行计算机仿真研究。
Level by Level Learning for Artificial Neuronal Groups is proposed in this paper. The learning process suggested by the method is more similar to the process of knowledge growth for human individual and society, and can improve generalization ability and learning efficiency for network. This paper carries out some case studies.
出处
《电子学报》
EI
CAS
CSCD
北大核心
1992年第10期39-43,81,共6页
Acta Electronica Sinica
基金
国家自然科学基金重大研究项目资助课题
关键词
逐层学习
神经网络
Artificial neuronal groups, Level by level learning
