摘要
针对跨越–侧抑制神经网络(Span-lateral inhibition neural network, S-LINN)的结构调整及参数学习问题,结合生物神经系统中神经元的稀疏连接特性,依据儿童及青少年智力发展水平与大脑皮层发育之间的相互关系,提出以小世界网络连接模式进行初始稀疏化的连接自组织发育稀疏跨越–侧抑制神经网络设计方法.定义网络连接稀疏度及神经元输出贡献率,设计网络连接增长–修剪规则,根据智力超常组皮层发育与智力水平的对应关系调整和控制网络连接权值,动态调整网络连接实现网络智力的自组织发育.通过非线性动力学系统辨识及函数逼近基准问题的求解,证明在同等连接复杂度的情况下,稀疏连接的跨越–侧抑制神经网络具有更好的泛化能力.
Inspired by the sparse connection of neurons in biological nervous system and the relationship between children and adolescents intellectual ability and cortical development, a connection self-organization development-based sparse span-lateral inhibition neural network(s S-LINN) is developed to solve the structure adjustment and parameter learning problem, which adopts the small-world network connection mode as the initial sparse network architecture. A growing-pruning rule of network connection is designed to adjust and control the sparseness of network connections based on the definitions of connection sparseness and neuron output contribution rate. Performance of the proposed sparse S-LINN is evaluated successfully through simulation using nonlinear dynamic system identification and function approximation benchmark problems. It is shown that the proposed s S-LINN can produce a very compact structure with good generalization ability in comparison with other methods.
作者
杨刚
王乐
戴丽珍
杨辉
YANG Gang;WANG Le;DAI Li-Zhen;YANG Hui(School of Electrical and Automation Engineering, East China Jiaotong University, Nanchang 330013;Key Labora- tory of Advanced Control and Optimization of Jiangxi Province, Nanchang 330013)
出处
《自动化学报》
EI
CSCD
北大核心
2019年第4期808-818,共11页
Acta Automatica Sinica
基金
国家自然科学基金(61663012
61673172
61733005)
国家留学基金(201509795007)
江西省自然科学基金(20161BAB212054)
江西省教育厅科技项目(GJJ150490)
江西省交通运输厅科技项目(2014X0015)资助~~
关键词
跨越–侧抑制神经网络
稀疏
小世界网络
智力发展
Span-lateral inhibition neural network(S-LINN)
spares
small-world network
intelligence development
