Abstract
Designing neural networks for object recognition requires considerable architecture engineering. As a remedy, neuro-evolutionary network architecture search, which automatically searches for optimal network architectures using evolutionary algorithms, has recently become very popular. Although very effective, evolutionary algorithms rely heavily on having a large population of individuals (i.e., network architectures) and is therefore memory expensive. In this work, we propose a Regularized Evolutionary Algorithm with low memory footprint to evolve a dynamic image classifier. In details, we introduce novel custom operators that regularize the evolutionary process of a micro-population of 10 individuals. We conduct experiments on three different digits datasets (MNIST, USPS, SVHN) and show that our evolutionary method obtains competitive results with the current state-of-the-art.
Abstract (translated)
设计用于对象识别的神经网络需要大量的体系结构工程。神经进化网络体系结构搜索作为一种补救方法，近年来得到了广泛的应用。虽然非常有效，但是进化算法很大程度上依赖于拥有大量的个体（即网络体系结构），因此内存非常昂贵。在这项工作中，我们提出了一个规则化的低内存足迹的进化算法来发展一个动态图像分类器。详细地介绍了一种新的自定义算子，它可以规范10个个体的微群体的进化过程。我们对三种不同的数字数据集（mnist、usps、svhn）进行了实验，结果表明，我们的进化方法获得了与当前最先进水平相竞争的结果。
URL
https://arxiv.org/abs/1905.06252
