Introduction

Machine Learning is proving to be a very powerful tool with applications in a diverse set of fields. However, oftentimes it is extremely difficult to figure out how to get started learning ML. I've listed below a few links to resources that I've personally found helpful (they're in rough order of ascending difficulty/experience): ML@B has been a working on a Machine Learning Crash Course series (WIP) that you can read: https://ml.berkeley.edu/blog/tutorials/ Andrew Ng's Machine Learning Coursera class is where I started learning about ML, and I think it's a great starting point: https://www.coursera.org/learn/machine-learning The online book Neural Networks and Deep Learning is great for getting into more detail about how various kinds of neural nets work: http://neuralnetworksanddeeplearning.com/ Chris Olah's blog has a lot of great posts about getting a visual, intuitive, and mathematical understanding of neural nets, CNNs, RNNs, etc: http://colah.github.io/ UC Berkeley's CS189/289A lecture notes give decent coverage of a lot of ML topics: https://people.eecs.berkeley.edu/~jrs/189s16/ Andrej Karpathy's blog also has a lot of good stuff on various ML stuff, but is more technical and programming heavy in nature: http://karpathy.github.io/ If you want to read about recent ML/AI progress from a more academic standpoint, I've been personally compiling a list of relevant/interesting papers: https://docs.google.com/document/d/1crt8810kbi1dcddsWp8Jgs7UWm5izzi9KJ5u8MHaRE0/edit?usp=sharing