I finally decided to take a graduate course on Machine learning. This was my last term at Western, and I needed one-course credit to graduate on time. I decided to spend some time learning machine learning to which I have very little exposure. Plus it will be something exciting and practical. I did not want to spend time solving equations and calling myself a machine learning engineer. (People who want to dig deeper and have an interest in it should. It was for me.) I wanted to build stuff and know enough theory to apply it.
A good course that had a good mix of theory and practice was Dr. Charles Ling’s
Advanced Machine Learning course. It was a tour of basic to advanced machine learning concepts with Kaggle Competitions and assignments to solidify the learning. I had a lot of fun with the course as it was a totally asynchronous course where I could learn the recorded lectures and solve assignments on my own time. The gamification of assignments on Kaggle was even more enjoyable.
I highly recommend Kaggle to learn practical aspects of machine learning and apply them. I will create a separate post with good resources to learn machine learning and build products with them. If you are interested in theory and want to write papers or get into a Ph.D. Programme in the same, by all means, goes ahead with classic courses from MIT and Standford, which I will also link in the post. But for the rest of us old school Software Engineers, practical knowledge will do.
I will post the link to the post below when it is up.