arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.15604cs.LGcs.NEstat.ML
收藏

神经网络中的层稀疏性

Layer Sparsity in Neural Networks

Université de Marne-la-Vallée(马恩河谷大学);Ruhr-University Bochum(鲁尔大学波鸿分校)

Mohamed Hebiri, Johannes Lederer

摘要:

稀疏性在机器学习中很受欢迎,因为它可以节省计算资源,便于解释,并防止过拟合。本文在神经网络的框架下讨论稀疏性。特别是,我们提出了一个新的稀疏性概念,它涉及到网络的各个层,因此与当前深度网络的趋势特别一致。我们称这个概念为层稀疏性。然后,我们介绍了相应的正则化和改装方案,可以补充标准的深度学习管道,以生成更紧凑和准确的网络。

英文摘要:

Sparsity has become popular in machine learning, because it can save computational resources, facilitate interpretations, and prevent overfitting. In this paper, we discuss sparsity in the framework of neural networks. In particular, we formulate a new notion of sparsity that concerns the networks' layers and, therefore, aligns particularly well with the current trend toward deep networks. We call this notion layer sparsity. We then introduce corresponding regularization and refitting schemes that can complement standard deep-learning pipelines to generate more compact and accurate networks.

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。

↑