Mathematical Principles in word2vec (iii) Background Knowledge

      
Word2vec is a toolkit launched by Google in 2013 by open source for obtaining word vector. It is simple and efficient, so it attracted the attention of many people. Because Tomas Mikolov, author of word2vec, did not talk about too many algorithm details in two related papers [3, 4], he added the magic of this toolkit to a certain extent. Some people who couldn't help but choose to look at it through source code anatomy. Out of curiosity, I became one of them. After reading the code, I think that I have gained a lot. I will write it into my documents and give some friends who need it an exam.

Related Links

(1) folders and Preface

(2) Prerequisites

(3) Background Knowledge

(4) Hierarchical softmax-based model

(5) Negative sampling-based model

(6) several source code details

Author: peghoty

Source: http://blog.csdn.net/itplus/article/details/37969817

You are welcome to repost/share the article, but be sure to declare the source of the article.