arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1801.01563cs.NE
收藏

DENSER:深度进化网络结构化表示

DENSER: Deep Evolutionary Network Structured Representation

Filipe Assunção, Nuno Lourenço, Penousal Machado, Bernardete Ribeiro

摘要:

深度进化网络结构化表示(DENSER)是一种利用演化计算自动设计人工神经网络(ANN)的新方法。该算法不仅搜索最佳网络拓扑(例如,层的数量、层的类型),而且还调谐超参数,例如学习参数或数据增强参数。使用具有两个不同级别的表示来实现自动设计,其中外部级别编码网络的一般结构,即,层的序列和内部层编码与每一层相关联的参数。超参数值的允许层和范围通过人类可读的上下文无关文法来定义。DENSER被用来发展人工神经网络CIFAR-10,获得94.13%的平均测试精度。在MNIST、Fashion-MNIST和CIFAR-100上测试了为CIFA-10进化的网络;结果具有很强的竞争力,在CIFAR-100上,我们报告了78.75%的测试准确度。据我们所知,我们的CIFAR-100结果是针对卷积神经网络(CNN)自动设计方法生成的性能最高的模型,并且是手动设计和微调CNN的最佳模型之一。

英文摘要:

Deep Evolutionary Network Structured Representation (DENSER) is a novel approach to automatically design Artificial Neural Networks (ANNs) using Evolutionary Computation. The algorithm not only searches for the best network topology (e.g., number of layers, type of layers), but also tunes hyper-parameters, such as, learning parameters or data augmentation parameters. The automatic design is achieved using a representation with two distinct levels, where the outer level encodes the general structure of the network, i.e., the sequence of layers, and the inner level encodes the parameters associated with each layer. The allowed layers and range of the hyper-parameters values are defined by means of a human-readable Context-Free Grammar. DENSER was used to evolve ANNs for CIFAR-10, obtaining an average test accuracy of 94.13%. The networks evolved for the CIFA--10 are tested on the MNIST, Fashion-MNIST, and CIFAR-100; the results are highly competitive, and on the CIFAR-100 we report a test accuracy of 78.75%. To the best of our knowledge, our CIFAR-100 results are the highest performing models generated by methods that aim at the automatic design of Convolutional Neural Networks (CNNs), and are amongst the best for manually designed and fine-tuned CNNs.

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。

↑