BriefGPT.xyz
Dec, 2018
层级softmax在大规模分类任务中的有效性
Effectiveness of Hierarchical Softmax in Large Scale Classification Tasks
HTML
PDF
Abdul Arfat Mohammed, Venkatesh Umaashankar
TL;DR
本文比较了 Softmax 和 Hierarchical Softmax 对于 LSHTC 数据集的性能表现，结果发现在类别数量较多时，Hierarchical Softmax 的表现会下降。
Abstract
Typically,
softmax
is used in the final layer of a
neural network
to get a probability distribution for output classes. But the main problem with
→