BriefGPT.xyz
Jul, 2015
信息筛选器
The Information Sieve
HTML
PDF
Greg Ver Steeg, Aram Galstyan
TL;DR
本文提出了一种基于层次信息分解的无监督学习表示法，针对离散变量的具体实现应用于多个基础任务，包括独立成分分析、有损和无损压缩以及数据中缺失值的预测。
Abstract
We introduce a new framework for
unsupervised learning
of deep representations based on a novel
hierarchical decomposition
of information. Intuitively, data is passed through a series of progressively fine-graine
→