For those considering an autodidactic alternative, this is for you. You can't go deeply into every machine learning topic. There's too much to learn, and the field is advancing rapidly. Motivation is far more important than micro-optimizing a learning strategy for some long-term academic or career goal. If you're trying to force yourself forward, you'll slow down.
It just occurred to me, that after a couple of years tracking Deep Learning developments, that nobody has even bothered to create a map of what's going on! So I quickly decided to come up with a Deep Learning roadmap. A word of warning, this is just a partial map and doesn't cover the latest developments. Many of the ideas I write on this blog isn't even covered by this map. Anyway, here's a start of this and hope people start coming out of their labs to further expand on it.
Machine Learning thrives on data. It is very important to understand the nature of underlying data on top of which the machine learning model is required to be built. Given a dataset, one of the first thing you would normally do is try to understand the nature and variety of data present in the dataset. This usually becomes the first stepping stone of creating a powerful and robust machine learning model. Statistics is a distant cousin of machine learning which also deals with data.