期刊
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
卷 24, 期 2, 页码 350-364出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TEVC.2019.2924461
关键词
Computer architecture; Training; Prediction algorithms; Optimization; Sociology; Statistics; Convolutional neural network (CNN); evolutionary deep learning (EDL); performance predictor; random forest; surrogate model
资金
- National Natural Science Foundation of China [61803277]
- Fundamental Research Funds for the Central Universities
- National Natural Science Fund of China for Distinguished Young Scholar [61625204]
- Marsden Fund of New Zealand Government [VUW1209, VUW1509, VUW1615]
- Huawei Industry Fund [E2880/3663]
- University Research Fund at Victoria University of Wellington [209862/3580, 213150/3662]
Convolutional neural networks (CNNs) have shown remarkable performance in various real-world applications. Unfortunately, the promising performance of CNNs can be achieved only when their architectures are optimally constructed. The architectures of state-of-the-art CNNs are typically handcrafted with extensive expertise in both CNNs and the investigated data, which consequently hampers the widespread adoption of CNNs for less experienced users. Evolutionary deep learning (EDL) is able to automatically design the best CNN architectures without much expertise. However, the existing EDL algorithms generally evaluate the fitness of a new architecture by training from scratch, resulting in the prohibitive computational cost even operated on high-performance computers. In this paper, an end-to-end offline performance predictor based on the random forest is proposed to accelerate the fitness evaluation in EDL. The proposed performance predictor shows the promising performance in term of the classification accuracy and the consumed computational resources when compared with 18 state-of-the-art peer competitors by integrating into an existing EDL algorithm as a case study. The proposed performance predictor is also compared with the other two representatives of existing performance predictors. The experimental results show the proposed performance predictor not only significantly speeds up the fitness evaluations but also achieves the best prediction among the peer performance predictors.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据