Keras

Everyday we deal with online platforms that use recommendation systems. There are different approaches to implement such systems and it depends on the product, the available data and more. This post will mainly focus on collaborative filtering using embeddings as a way to learn about latent factors. I learned about this approach months ago from fast.ai Practical Deep Learning for Coders lessons. I also found out that StichFix wrote about the same concept in a blog post last year Understanding Latent Style. [Read More]

In part 1 and part 2 of this series of posts on Text Classification in Keras we got a step by step intro about: processing text in Keras. embedding vectors as a way of representing words. defining a sequential models from scratch. Since we are working with a real dataset from the Toxic Comment Classification Challenge on Kaggle, we can always see how our models would score on the leaderboard if we competed with the final submissions. [Read More]

In the previous post, we had an overview about text pre-processing in keras. In this post we will use a real dataset from the Toxic Comment Classification Challenge on Kaggle which solves a multi-label classification problem. In this competition, it was required to build a model that’s “capable of detecting different types of toxicity like threats, obscenity, insults, and identity-based hate”. The dataset includes thousands of comments from Wikipedia’s talk page edits and each comment can have more than one tag. [Read More]

Keras provides a simple and flexible API to build and experiment with neural networks. I used it in both python and R, but I decided to write this post in R since there are less examples and tutorials. This series of posts will focus on text classification using keras. The introductory post will show a minimal example to explain: text pre-processing in keras. how and why to use embeddings. [Read More]