Word Embeddings

Word Vectors are a reprentation of words as a vector of numbers.

Log Loss Explained

We applied “log loss” and trained until convergence

Dynamic Coattention Networks

This paper aims to provide a model for QA. It encorporates a novel co attention system between the question and the passage. The basic gist of this paper is that attention is usually calculated for a single entity, or vector. In this paper , they devised a mechanism to create attention vectors for two vectors/modalities, the passage and the question.

Lets Make A Chrome Extension

An introduction to extension programming wherein we make a torrent scrapping chrome extension !