基于神经元对齐的神经网络安全交叉
Safe Crossover of Neural Networks Through Neuron Alignment
摘要：
在使用遗传算法进化神经网络的权重时，一个主要的且很大程度上未被探索的挑战是在父网络之间找到一个合理的交叉操作。事实上，幼稚的交叉导致功能受损的后代不能保留来自父母的信息。这是因为神经网络对神经元的排列是不变的，从而产生了表示相同解的多种方式。这通常被称为竞争公约问题。在本文中，我们提出了一个两步安全交叉（SC）运营商。首先，父母的神经元通过计算它们之间的相关程度而在功能上对齐，只有这样父母才能重组。我们比较了两种测量神经元之间关系的方法：成对相关（PwC）和典型相关分析（CCA）。通过对前馈神经网络对的权重进行算术交叉，我们在MNIST和CIFAR-10上测试了我们的安全交叉算子（SC-PwC和SC-CCA）。我们表明，它有效地将信息从父母传递给后代，并显着提高了天真的交叉。我们的方法计算速度快，可以作为一种更有效地探索适应度景观的方法，并使安全交叉在未来的神经进化研究和应用中成为一个潜在的有前途的算子。
英文摘要：
One of the main and largely unexplored challenges in evolving the weights of neural networks using genetic algorithms is to find a sensible crossover operation between parent networks. Indeed, naive crossover leads to functionally damaged offspring that do not retain information from the parents. This is because neural networks are invariant to permutations of neurons, giving rise to multiple ways of representing the same solution. This is often referred to as the competing conventions problem. In this paper, we propose a two-step safe crossover(SC) operator. First, the neurons of the parents are functionally aligned by computing how well they correlate, and only then are the parents recombined. We compare two ways of measuring relationships between neurons: Pairwise Correlation (PwC) and Canonical Correlation Analysis (CCA). We test our safe crossover operators (SC-PwC and SC-CCA) on MNIST and CIFAR-10 by performing arithmetic crossover on the weights of feed-forward neural network pairs. We show that it effectively transmits information from parents to offspring and significantly improves upon naive crossover. Our method is computationally fast,can serve as a way to explore the fitness landscape more efficiently and makes safe crossover a potentially promising operator in future neuroevolution research and applications.
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。
