As I am very interested in Data Science and its applications and I have an idea for a Master's thesis that requires Machine Learning, I was keen on learning the basics of what Artificial Intelligence is all about.

A quick internet research led me to Andrew Ng's Machine Learning Specialization. It consists of three parts. The first, Supervised Machine Learning: Regression and Classification, gives an insight into basic algorithms using scikit-learn and the math behind them. In a second part called Advanced Learning Algorithms, neural networks are introduced, manually and using TensorFlow, as well as decision trees and tree ensemble methods. Finally, in Unsupervised Learning, Recommenders, Reinforcement Learning, one learns about unsupervised clustering and anomaly detection, recommender systems with a collaborative filtering approach and a deep reinforcement learning model.

The course is intended for a very broad spectrum of students, which is why people with a minimal math background can cruise through the first parts. Overall I learned very much, but as always, true proficiency will only follow after implementing the methods myself many times and without the guiding environment Ng and his team provide during the course. However, to start learning, this help was very much appreciated.

You can see my certificate of completion and 100% grade here.