Competitive two-island cooperative co-evolution for training feedforward neural networks for pattern classification problems
Competitive two-island cooperative co-evolution for training feedforward neural networks for pattern classification problems
复制标题
DOI：
10.1109/ijcnn.2015.7280349
复制
发表时间：
2015-07
期刊：
影响因子：
--
通讯作者：
Rohitash Chandra;Gary Wong
中科院分区：
文献类型：
--
作者：
Rohitash Chandra;Gary Wong
在协同进化神经进化的应用中，问题分解方法依赖于神经网络的结构属性将其划分为子组件。在进化过程的每个阶段，不同的问题分解方法产生独特的特征，这些特征在支持解决方案共享的环境中可能是有用的。在本文中，我们实现了两个岛屿的竞争环境中的合作协同进化的神经进化的前馈神经网络模式分类问题。特别是三种问题分解方法的组合，这三种方法是基于神经元级、网络级和层级分解的体系结构特性。实验结果表明，竞争方法的性能优于独立的问题分解合作神经进化方法。
In the application of cooperative coevolution for neuro-evolution, problem decomposition methods rely on architectural properties of the neural network to divide it into subcomponents. During every stage of the evolutionary process, different problem decomposition methods yield unique characteristics that may be useful in an environment that enables solution sharing. In this paper, we implement a two-island competition environment in cooperative coevolution based neuro-evolution for feedforward neural networks for pattern classification problems. In particular the combinations of three problem decomposition methods that are based on the architectural properties that refers to neural level, network level and layer level decomposition. The experimental results show that the performance of the competition method is better than that of the standalone problem decomposition cooperative neuro-evolution methods.