http://mp.weixin.qq.com/s?__biz=MzAwMjM3MTc5OA==&mid=404476249&idx=1&sn=8c1449057d8af89cf0a0cfea8169abdf&scene=0#wechat_redirect

\1. 《BinaryNet: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1》

\3. 《Swivel: Improving Embeddings by Noticing What’s Missing》

\4. 《Random Walks on Context Spaces: Towards an explanation of the mysteries of semantic word embeddings》

BinaryNet: +1 or -1

Swivel: Improving Embeddings