arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1604.04153cs.NE
收藏

用神经网络学习生成基因型

Learning to Generate Genotypes with Neural Networks

Alexander W. Churchill, Siddharth Sigtia, Chrisantha Fernando

摘要:

神经网络和演化计算有着丰富的相互交织的历史。当进化算法优化强化学习问题的神经网络的参数和拓扑结构时,或者当神经网络被用作替代适应度函数以帮助昂贵的适应度函数的进化优化时,它们最常一起出现。在本文中,我们采取了不同的方法,问的问题是否可以使用神经网络提供一个进化算法的突变分布,这种方法可能提供什么优势?本文研究了两种现代神经网络模型,一种改进的产生随机输出的去噪自编码器和神经自回归分布估计器。结果表明,神经网络的方法来学习基因型是能够解决许多困难的离散问题,如MaxSat和HIFF,并定期优于其他进化技术。

英文摘要:

Neural networks and evolutionary computation have a rich intertwined history. They most commonly appear together when an evolutionary algorithm optimises the parameters and topology of a neural network for reinforcement learning problems, or when a neural network is applied as a surrogate fitness function to aid the evolutionary optimisation of expensive fitness functions. In this paper we take a different approach, asking the question of whether a neural network can be used to provide a mutation distribution for an evolutionary algorithm, and what advantages this approach may offer? Two modern neural network models are investigated, a Denoising Autoencoder modified to produce stochastic outputs and the Neural Autoregressive Distribution Estimator. Results show that the neural network approach to learning genotypes is able to solve many difficult discrete problems, such as MaxSat and HIFF, and regularly outperforms other evolutionary techniques.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑