【论文】深度学习的数学解释

点击上方 “机器学习研究会”可以订阅

摘要

 

转自：爱可可-爱生活

论文《Mathematics of Deep Learning》摘要：

Recently there has been a dramatic increase in the performance of recognition systems due to the introduction of deep architectures for representation learning and classification. However, the mathematical reasons for this success remain elusive. This tutorial will review recent work that aims to provide a mathematical justification for several properties of deep networks, such as global optimality, geometric stability, and invariance of the learned representations.

链接：

https://arxiv.org/abs/1712.04741

原文链接：

https://m.weibo.cn/1402400261/4185078643259649

“完整内容”请点击【阅读原文】

↓↓↓