Week 9 (27/08/18 - 31/08/18)
ISB Videos This week we ended our ISB's Machine Learning course with the last two lectures which were on Text Analysis and Mining graphs. The topics covered were as follows: Word2vec Word2vec is a two-layer neural net that processes text. Its input is a text corpus and its output is a set of vectors: feature vectors for words in that corpus. While Word2vec is not a deep neural network , it turns text into a numerical form that deep nets can understand. The purpose and usefulness of Word2vec are to group the vectors of similar words together in vector space. That is, it detects similarities mathematically. Word2vec creates vectors that are distributed numerical representations of word features, features such as the context of individual words. It does so without human intervention. T here are two types of Word2Vec, Skip-gram and Continuous Bag of Words (CBOW). I will briefly describe how these two methods work in the following paragraphs. Skip-gram Words are ...