I've been spending my free time getting myself familiar with ML and personally I'm focused on resharpening my math skills, reading papers from the "awesome deep learning papers" repo [1], playing with TensorFlow, and reading the Neural Networks and Deep Learning book [2]. I did my undergrad degree in math, so a lot of the math is just review for me, but ML seems to get fairly math heavy pretty quick. I would suggest anyone looking at ML to spend a good amount of time going through the backing math in addition to the CS parts, otherwise you might not develop much intuition for what's going on.

[1] https://github.com/terryum/awesome-deep-learning-papers

[2] http://neuralnetworksanddeeplearning.com/