BriefGPT.xyz
Jul, 2017
探究基于少量先验知识的领域内迁移学习和小样本学习
A Brief Study of In-Domain Transfer and Learning from Fewer Samples using A Few Simple Priors
HTML
PDF
Marc Pickett, Ayush Sekhari, James Davidson
TL;DR
本文研究了对于领域结构未知，需要从数据中学习结构和参数的系统是否能够通过学习结构来降低样本复杂度，为至少两种简单情况证明了结构学习降低样本复杂度的可行性，并探究了如何在更复杂的情况下实现这一目标。
Abstract
domain knowledge
can often be encoded in the structure of a network, such as
convolutional layers
for vision, which has been shown to increase generalization and decrease
→