论文标题
进化深度学习的调查：原理，算法，应用和开放问题
Survey on Evolutionary Deep Learning: Principles, Algorithms, Applications and Open Issues
论文作者
论文摘要
近年来，行业和学术界的深度学习（DL）迅速发展。但是，找到DL模型的最佳超参数通常需要高计算成本和人类专业知识。为了减轻上述问题，进化计算（EC）作为一种强大的启发式搜索方法，在DL模型的自动设计（所谓的进化深度学习（EDL））中表现出了重要优势。本文旨在从自动化机器学习（AUTOML）的角度分析EDL。具体来说，我们首先从机器学习和EC阐明EDL，并将EDL视为优化问题。根据DL管道的说法，我们系统地介绍了EDL方法，从功能工程，模型生成到具有新的分类法（即演变/优化的内容以及如何发展/优化）的模型部署，并专注于解决解决方案表示和搜索范式的讨论，以通过EC处理优化问题。最后，提出了关键的应用程序，开放问题以及可能有希望的未来研究线。这项调查已经回顾了EDL的最新发展，并为EDL的开发提供了有见地的指南。
Over recent years, there has been a rapid development of deep learning (DL) in both industry and academia fields. However, finding the optimal hyperparameters of a DL model often needs high computational cost and human expertise. To mitigate the above issue, evolutionary computation (EC) as a powerful heuristic search approach has shown significant merits in the automated design of DL models, so-called evolutionary deep learning (EDL). This paper aims to analyze EDL from the perspective of automated machine learning (AutoML). Specifically, we firstly illuminate EDL from machine learning and EC and regard EDL as an optimization problem. According to the DL pipeline, we systematically introduce EDL methods ranging from feature engineering, model generation, to model deployment with a new taxonomy (i.e., what and how to evolve/optimize), and focus on the discussions of solution representation and search paradigm in handling the optimization problem by EC. Finally, key applications, open issues and potentially promising lines of future research are suggested. This survey has reviewed recent developments of EDL and offers insightful guidelines for the development of EDL.
