RCE网络即“衰减库仑势”法，在每一个模式层单元都有一个对应的超球体半径可调整的参数。有与概率神经网络相同的拓扑结构。-RCE network that is " attenuated Coulomb potential" method, a model layer in each unit has a corresponding super-sphere radius of adjustable parameters. With the probabilistic neura

拓扑优化的经典程序，实施过程中采用conv2 Matlab function。希望对对您有所帮助.-The classic topology optimization procedures, the implementation process used conv2 Matlab function. Hope for your help.

一类新的神经进化算法——NEAT，可同步进化BP网络的拓扑结构和连接权值，避免了网络结构的选择和设计，此程序是用于解决经典的XOR分类问题-A new neuroevolution algorithm is called NEAT.NEAT can evolve the topologies as well as the connection weights of BP network. this matlab program solves the XOR problem.