神经网络设计的高效自动化：可微分神经架构搜索综述（英文版）

英文标题：Efficient Automation of Neural Network Design: A Survey on Differentiable Neural Architecture Search中文摘要：该论文综述了 Differentiable Neural Architecture Search (DNAS) 领域的最新进展，提出了一种基于挑战的分类方法，并探讨了 DNAS 对全局神经架构搜索领域的影响和未来研究方向。英文摘要：In the past few years, Differentiable Neural Architecture Search (DNAS)rapidly imposed itself as the trending approach to automate the discovery ofdeep neural network architectures. This rise is mainly due to the popularity ofDARTS, one of the first major DNAS methods. In