Augustina C. Amakor, Konstantin Sontag, Sebastian Peitz
TL;DR稀疏性、深度神经网络、正则化路径、经验损失和帕累托前沿是研究论文的主要关键词和研究领域。
Abstract
sparsity is a highly desired feature in deep neural networks (DNNs) since it ensures numerical efficiency, improves the interpretability of models (due to the smaller number of relevant features), and robustness.