A new hybrid neural-genetic methodology for improving learning
A new hybrid neural-genetic methodology for improving learning
复制标题
一种用于改善学习的新混合神经遗传方法
DOI：
10.1109/tai.1997.632233
复制
发表时间：
1997
期刊：
影响因子：
--
通讯作者：
L. Tsoukalas
中科院分区：
文献类型：
--
作者：
A. Likartsis;I. Vlachavas;L. Tsoukalas
提出了一种新的混合神经-遗传方法，该方法利用遗传算法的优化优势来加速神经网络的训练。适应度函数的选择和实验结果表明，神经网络的训练，通过所提出的方法得到改善。结果表明，遗传算法可以成为一个强大的工具，以改善神经网络的学习。
A new hybrid neural-generic methodology is presented that exploits the optimization advantages of genetic algorithms for the purpose of accelerating neural network training. The choice of fitness function is addressed and experimental findings are shown where neural network training is improved through the proposed approach. The results suggest that genetic algorithms can be a powerful tool for improving learning in neural networks.