错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

Why Rectified Linear Unit Is Efficient in Machine Learning: One More Explanation

  • Barnabas Bede,
  • Vladik Kreinovich,
  • Uyen Pham

摘要

In many applications, in particular, in econometric application, deep learning techniques are very effective. In this paper, we provide a new explanation for why rectified linear units—the main units of deep learning—are so effective. This explanation is similar to the usual explanation of why Gaussian (normal) distributions are ubiquitous—namely, it is based on an appropriate limit theorem.