摘要
本文首先给出二进前向多层网几何学习算法[1，2]的一个改进策略，提高了原算法的学习效率．然后提出一个新的神经网络启发式遗传几何学习算法（简称HGGL算法）．H～算法采用面向知识的交叉算子和变异算子对几何超平面进行优化的划分，同时确定隐层神经元的个数及连接权系数和阈值对任意布尔函数。
A modification to the geometrical learning algorithm of binary neural network, which tries to enhance efficiency of the algorithm, is demonstrated. Then a new Heuristic Genetic Geometrical Learning algorithm(called HGGL algorithm) of the neural network used for arbitrary Boolean function approximation is presented. The algorithm imtroducesknowledge based crossover operator and mutation operator to optimally divede geometrical hypercube and evaluate the numberof the hidden netirons, connection weight and threshold. For arbitrary Boolean function, the neural network trained by HGGLalgorithm has the fewest number of hidden layer neurons comparde with existed leaning algorithms.
出处
《电子学报》
EI
CAS
CSCD
北大核心
1999年第12期110-112,共3页
Acta Electronica Sinica
基金
国家自然科学基金!69772035
69882002
国家"863"资助
关键词
遗传算法
神经网络
学习算法
布尔函数
genetic algorithm
neural network
learning algorithm
Boolean function
