arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2107.12801cs.LGmath.OC
收藏

基于可达性方法训练浅层神经网络的鲁棒优化框架

Robust Optimization Framework for Training Shallow Neural Networks Using Reachability Method

Southwest Jiaotong University(西南交通大学);Augusta University(奥古斯塔大学)

Yejiang Yang, Weiming Xiang

摘要:

基于神经网络的可达性分析,提出了一种用于训练浅层神经网络的鲁棒优化框架。为了表征输入数据的噪声,在区间集的描述中对输入训练数据进行扰动。然后对隐藏层进行基于区间的可达性分析。在鲁棒最小二乘问题框架下,利用可达性分析结果,提出了一种鲁棒优化训练方法。然后,发达国家的鲁棒最小二乘问题放松到一个半定规划问题。结果表明,所提出的鲁棒学习方法可以在一定程度上以损失训练精度为代价,提供更好的鲁棒性。最后,通过一个机器人手臂模型学习实例对该方法进行了验证.

英文摘要:

In this paper, a robust optimization framework is developed to train shallow neural networks based on reachability analysis of neural networks. To characterize noises of input data, the input training data is disturbed in the description of interval sets. Interval-based reachability analysis is then performed for the hidden layer. With the reachability analysis results, a robust optimization training method is developed in the framework of robust least-square problems. Then, the developed robust least-square problem is relaxed to a semidefinite programming problem. It has been shown that the developed robust learning method can provide better robustness against perturbations at the price of loss of training accuracy to some extent. At last, the proposed method is evaluated on a robot arm model learning example.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑