论文标题
通过低分配序列培训来提高深度学习算法的准确性
Enhancing accuracy of deep learning algorithms by training with low-discrepancy sequences
论文作者
论文摘要
我们提出了一种基于低分配序列作为训练集的深入监督学习算法。通过理论参数和广泛的数值实验的结合，我们证明了所提出的算法明显优于基于随机选择的培训数据的标准深度学习算法，这些算法是中等较高维度的问题。所提出的算法为在科学计算的背景下为许多基础地图构建廉价替代物提供了一种有效的方法。
We propose a deep supervised learning algorithm based on low-discrepancy sequences as the training set. By a combination of theoretical arguments and extensive numerical experiments we demonstrate that the proposed algorithm significantly outperforms standard deep learning algorithms that are based on randomly chosen training data, for problems in moderately high dimensions. The proposed algorithm provides an efficient method for building inexpensive surrogates for many underlying maps in the context of scientific computing.
