Machine Learning with real-world data

There are a huge number of ML methods, with new variants being invented every day. But the ways that one works with these various methods are very similar. Hence we are teaching this course to give students an introduction to the methodological and experimental issues involved in working with ML. To a large extent, the principles of good experimental practice are the same whether one is using a well-known and simple approach or a deep-learning method that was developed last month. We’re going to concentrate on the simple methods in this course, so that students can fully understand what’s going on without having a very detailed description of a highly complex algorithm. But the principles we cover also apply to experiments with state-of-the-art methods.