1引言泛函网络(Functional networks)是Castillo E在1998年提出的一种网络模型[1,2],是人工神经网络的一种有效扩展,它处理的是一般的泛函模型。
基于16个网页-相关网页
recurrent functional networks 递归泛函网络
Orthogonal functional networks 正交泛函网络
functional brain networks 功能性脑网络
functional link artificial neural networks 接型神经网络 ; 神经网络
Non-linear regression forecast model and learning algorithm based on functional networks are proposed in this article.
为此提出了基于泛函网络的非线性回归预测模型和相应的学习算法。
参考来源 - 基于泛函网络的非线性回归预测模型及学习算法·2,447,543篇论文数据，部分数据来源于NoteExpress
In this paper, by analyzing the functional network, a new model and learning algorithm of the serial functional networks is proposed.
通过对泛函网络的分析，提出了一种序列泛函网络模型及学习算法，而网络的泛函参数利用梯度下降法来进行学习。
The neurons form connections and self-assemble into functional networks, allowing us access to the same phenomena of plasticity that occur in vivo.
这些神经元在培养皿中形成连结并自我聚集成功能性网络，让我们能观察到与活体中相同的可塑性形成现象。
So, researching numerical computing by Evolution Strategy, Differential Evolution Algorithm and Functional Networks have higher theory value and practical significance.
因此用进化策略、差分演化算法、泛函网络来研究数值计算，有较高的理论价值和实际意义。
应用推荐