4.6 Article

Multi-objective simulated annealing for hyper-parameter optimization in convolutional neural networks

期刊

PEERJ COMPUTER SCIENCE
卷 -, 期 -, 页码 -

出版社

PEERJ INC
DOI: 10.7717/peerj-cs.338

关键词

Multi-objective; Simulated annealing; Convolutional neural networks; Hyper-parameter optimization

向作者/读者索取更多资源

The study models a CNN hyper-parameter optimization problem as a bi-criteria optimization problem and develops a MOSA algorithm for high-quality solutions. The MOSA algorithm performs better in a multi-objective setting on the CIFAR-10 dataset compared to the single-objective SA method.
In this study, we model a CNN hyper-parameter optimization problem as a bi-criteria optimization problem, where the first objective being the classification accuracy and the second objective being the computational complexity which is measured in terms of the number of floating point operations. For this bi-criteria optimization problem, we develop a Multi-Objective Simulated Annealing (MOSA) algorithm for obtaining high-quality solutions in terms of both objectives. CIFAR-10 is selected as the benchmark dataset, and the MOSA trade-off fronts obtained for this dataset are compared to the fronts generated by a single-objective Simulated Annealing (SA) algorithm with respect to several front evaluation metrics such as generational distance, spacing and spread. The comparison results suggest that the MOSA algorithm is able to search the objective space more effectively than the SA method. For each of these methods, some front solutions are selected for longer training in order to see their actual performance on the original test set. Again, the results state that the MOSA performs better than the SA under multi-objective setting. The performance of the MOSA configurations are also compared to other search generated and human designed state-of-the-art architectures. It is shown that the network configurations generated by the MOSA are not dominated by those architectures, and the proposed method can be of great use when the computational complexity is as important as the test accuracy.

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。

评论

主要评分

4.6
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据