暂态混沌神经网络中的模拟退火策略优化  

Optimal strategy for simulated annealing mechanics in transiently chaotic neural networks

作　　者：李薪宇[1] 吕炳朝[1] 

机构地区：[1]电子科技大学自动化工程学院,四川成都610054

出　　处：《计算机应用》2005年第10期2410-2412,共3页journal of Computer Applications

摘　　要：分析了暂态混沌神经网络(TCNN)模型的动力学特性对自反馈连接权值的敏感性,研究了退火函数对优化过程中的准确性和计算速度的影响。给出一种对模拟退火策略的优化算法,在保证优化算法准确性的基础上,加快收敛速度,并利用两个典型的函数优化的例子验证了这种优化策略的有效性。This paper analyzed that the dynamic characteristics of transiently chaotic networks （TCNN） quite sensitively depend on value of the self-feedback connection weights, and researched the annealing function that intensively influences the veracity and search speed of TCNN module. It is proposed an optimal strategy for value of the self-feedback connection weights that can accelerate the search speed and guarantee the assurance of the veracity of the optimal arithmetic. To demonstrate the validity of this optimal strategy, two examples of function optimization are given.

关 键 词：暂态混沌神经网络 自反馈连接权 函数优化 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]