Short Paper: A Multistage Backward Differentiable Method for Constructing Light Convolutional Neural Networks
2019 Second International Conference on Artificial Intelligence for Industries (AI4I)(2019)
摘要
We propose a multistage differentiable method to select convolutional channels and construct light neural networks from a heavy network for inference on a subset of a big data set. The selection proceeds backward in layers and utilizes sparse penalty to diversify channel scores. The resulting light network gains sizable accuracy over the baseline heavy network.
更多查看译文
关键词
differentiable channel selection, light network
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要