2017-ICLR-Neural Architecture Search with Reinforcement Learning 论文阅读
NAS with RL 2017-ICLR-Neural Architecture Search with Reinforcement Learning Google Brain Quoc V . Le etc GitHub: stars Citation:1499 Abstract we use a recurrent network to generate the model descriptions of neural networks and train this RNN with reinforcement learning to maximize the expected accuracy of the generated architectures on a validation set. 用RNN生成模型描述(边长的字符串),用RL(强化学习)训练RNN,来最大化模型在验证集上的准确率。 Motivation Along with this success is a paradigm shift from feature designing to architecture designing, 深度学习的成功是因为范式的转变:特征设计(SIFT、HOG)到结构设计(AlexNet、VGGNet)。 This paper presents Neural