Course Preview: Imperial Machine Learning for Decision Making

Ready to Learn More? Apply to Enroll in: Imperial Machine Learning for Decision Making

This module is going to provide an introduction to the vast area of machine learning. In particular, we are going to apply some fundamental understanding of the theory of machine learning to a broad class of algorithms that are commonly used in practice. There are going to be three paths to this module.

The first one is going to be a theoretical discussion on whether it is possible to learn it all and what can be learned. We will be using the theory of generalization bounds to give us some strong mathematical insight into when learning is feasible at all.

The second part is going to consist of an evaluation of machine learning algorithms. We will discuss how we can measure the performance of any given machine learning algorithm, how to decide whether that performance is satisfactory or not, and how to select the best of a number of machine learning algorithms.

In the third and final part of this course, we're going to discuss some of the most commonly used machine learning approaches. In particular, we are going to look at three different supervised learning techniques — k-nearest neighbors, Naïve Bayes, and decision trees.

Toward the end of this module, we will also look at an unsupervised learning technique, the so-called cluster analysis. As you will see, this course will be a mix of theoretical concepts as well as practical assignments. The reason for that is simple — I want to make sure that you understand the algorithms, how they work and why they work, but I also want you to figure out how to actually work with these algorithms in Python.

[End of Video Transcript]

Related Content: AI and Machine Learning Online Courses at Emeritus