当前位置: X-MOL 学术IEEE T. Evolut. Comput. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A Survey on Evolutionary Construction of Deep Neural Networks
IEEE Transactions on Evolutionary Computation ( IF 14.3 ) Pub Date : 2021-05-13 , DOI: 10.1109/tevc.2021.3079985
Xun Zhou , A. K. Qin , Maoguo Gong , Kay Chen Tan

Automated construction of deep neural networks (DNNs) has become a research hot spot nowadays because DNN’s performance is heavily influenced by its architecture and parameters, which are highly task-dependent, but it is notoriously difficult to find the most appropriate DNN in terms of architecture and parameters to best solve a given task. In this work, we provide an insight into the automated DNN construction process by formulating it into a multilevel multiobjective large-scale optimization problem with constraints, where the nonconvex, nondifferentiable, and black-box nature of this problem make evolutionary algorithms (EAs) to stand out as a promising solver. Then, we give a systematical review of existing evolutionary DNN construction techniques from different aspects of this optimization problem and analyze the pros and cons of using EA-based methods in each aspect. This work aims to help DNN researchers to better understand why, where, and how to utilize EAs for automated DNN construction and meanwhile, help EA researchers to better understand the task of automated DNN construction so that they may focus more on EA-favored optimization scenarios to devise more effective techniques.

中文翻译:

深度神经网络进化构建综述

深度神经网络 (DNN) 的自动化构建已成为当今的研究热点,因为 DNN 的性能很大程度上受其架构和参数的影响,这些架构和参数高度依赖于任务,但众所周知,在架构方面很难找到最合适的 DNN和参数以最好地解决给定的任务。在这项工作中,我们通过将其公式化为具有约束的多级多目标大规模优化问题来深入了解自动化 DNN 构建过程,其中该问题的非凸、不可微和黑盒性质使进化算法 (EA) 能够作为一个有前途的求解器脱颖而出。然后,我们从这个优化问题的不同方面系统地回顾了现有的进化 DNN 构建技术,并分析了在每个方面使用基于 EA 的方法的利弊。这项工作旨在帮助 DNN 研究人员更好地了解为什么、在哪里以及如何利用 EA 进行自动化 DNN 构建,同时帮助 EA 研究人员更好地理解自动化 DNN 构建的任务,以便他们可以更多地关注 EA 偏爱的优化场景设计更有效的技术。
更新日期:2021-05-13
down
wechat
bug