A list of useful properties and their proofs in linear algebra. Some of them are also very useful in machine learning. Complex proofs are not in the scope of the post, but the references will be given if interested.

The EM algorithm is used to find (local) maximum likelihood parameters of a statistical model in cases where the equations cannot be solved directly. Typically these models involve latent variables in addition to unknown parameters and known data observations. In this post, we will talk about how the algorithm works and then prove its correctness, finally we will show a concrete yet the most common use case where the algorithm is applied.

My thoughts on the qualification round of Google Hash Code 2019. If you are interested in the past Online Qualification Round and Finals problem statements, you should check this page.

A learning note of the coursera specialization Tensorflow in practice given by deeplearning.ai.

• Course 1: Introduction to TensorFlow for AI, ML and DL
• Course 2: Convolutional Neural Networks in TensorFlow
• Course 3: Natural Language Processing in TensorFlow
• Course 4: Sequences, Time Series and Prediction

A list of coding interview questions that I was asked in 2018.