原创:基于熵聚类的泛函网络神经元函数优化 - 科技论文发表 - xzbu.com 中国论文网 关键词:泛函网络;熵聚类;神经元函数 [gap=856]Key words: functional networks;entropy clustering; neuron function
基于28个网页-相关网页
然后,在此框架下提出了基于遗传规划的单个神经元的设计方法,该方法可实现对神经元函数类型的优化。
Then, based on GP the design algorithm of single neuron, which realizes the auto-optimization of neuron function types, is proposed.
新算法选择很广一类的隐层神经元函数,可以直接求得全局最小点,不存在BP算法的局部极小、收敛速度慢等问题。
The algorithm can get global minimum easily with a wide variety of functions of hidden neurons, and no problems such as local minima and slow rate of convergence are suffered like BP algorithm.
通过采用非线性函数作为神经元的传递函数,使神经网络的非线性问题同力学的非线性问题得到统一。
The analytical scheme of nonlinear contact mechanics is corresponded to that of Neural Network by Considering nonlinear functions as nerve cell translation functions.
应用推荐