This repo contains my notes and project while attending the Google Developers Machine Learning Bootcamp Malaysia that was held from October 29 to November 1, 2018 at Malaysian Global Innovation & Creativity Centre (MaGIC). The in-person bootcamp was based on the online Machine Learning Crash Course that was released by Google on March 2, 2018.
Google's Machine Learning Crash Course (MLCC) was created internally by Google and its engineering education team has delivered the course to more than 18,000 Googlers. MLCC covers many machine learning fundamentals, starting with loss and gradient descent, then building through classification models and neural nets.
On the last day of the bootcamp, we were required to complete a project in the form of a Kaggle-styled challenge. The challenge was about Toxic Comment Classification Challenge. The task was to build a multi-headed model that’s capable of detecting different types of toxicity like threats, obscenity, insults, and identity-based hate using a dataset of comments from Wikipedia’s talk page edits. The use case was to use the model to identify and classify toxic online comments to help online discussion become more productive and respectful. If you have completed the crash course earlier or just want to have a look at my project, feel free to jump straight to the Project section.
Source: Kaggle (https://www.kaggle.com/c/jigsaw-toxic-comment-classification-challenge)