综述基于强化学习的神经网络结构搜索方法及其优化进展。
A Survey on Neural Architecture Search Based on Reinforcement Learning
- 用强化学习自动搜寻最优神经网络结构
- 覆盖复杂结构与资源受限场景下的改进方案
- 适合对自动化模型设计感兴趣的读者
深度学习的迅猛发展已成功实现机器学习中特征提取的自动化。然而，深度神经网络的结构和超参数在不同任务中的表现差异显著。探索最优结构与超参数的过程通常需要大量人工干预。因此，自动化搜索最优网络结构与超参数成为迫切需求。超参数优化致力于自动化超参数选择，而神经架构搜索（Neural Architecture Search, NAS）则旨在针对特定任务自动寻找最佳网络结构。本文首先介绍神经架构搜索的整体发展历程，重点提供关于与强化学习相关的神经架构搜索工作的全面且易懂的综述，涵盖各类改进与变体，以满足更复杂结构及资源受限环境的需求。
原文摘要 · Abstract (English)
The automation of feature extraction of machine learning has been successfully realized by the explosive development of deep learning. However, the structures and hyperparameters of deep neural network architectures also make huge difference on the performance in different tasks. The process of exploring optimal structures and hyperparameters often involves a lot of tedious human intervene. As a result, a legitimate question is to ask for the automation of searching for optimal network structures and hyperparameters. The work of automation of exploring optimal hyperparameters is done by Hyperparameter Optimization. Neural Architecture Search is aimed to automatically find the best network structure given specific tasks. In this paper, we firstly introduced the overall development of Neural Architecture Search and then focus mainly on providing an overall and understandable survey about Neural Architecture Search works that are relevant with reinforcement learning, including improvements and variants based on the hope of satisfying more complex structures and resource-insufficient environment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。