Machine Learning (ML) is a sub-field of Artificial Intelligence that includes the techniques, models and algorithms that are used for developing a rational agent, which is a software application that can analyze its environment and make correct or effective decisions based on past experience. This course is an overview of ML designed for students with a technical background. This course is intended as a prerequisite to the more specialized ML courses.
This course is a technical introduction. Students must have a basic knowledge of statistics and mathematics equivalent to a first year of freshman university level course. Students must also have intermediate programming level experience. While Python is used as the primary ML language, students do not have to be Python programmers but should have enough programming experience to be able to follow an in class discussion of Python code. No previous experience with AI or ML is required.
5 Days Lecture/Lab
The course is designed for developers and technical leads who need a technical introduction and overview of ML that is extensive in scope rather than being an intensive deep dive into a specific ML methodology.
- To provide a comprehensive review of the current state the art in ML development.
- To develop a high level view of the different types of ML, how they are related and how they relate to other areas of AI such as autonomous agents and AI planning.
- To provide a technical introduction to the main concepts, algorithms, models and techniques used in ML applications.
- To explore the types of problems and domains that ML is being applied to and how well these applications perform, as well as examining their current strengths and weaknesses.
- To conduct a hands on review of the ML tools and platforms that are freely available to developers.
- The course covers the three main areas of ML: Supervised Learning, Unsupervised Learning, Reinforcement Learning and the variations on these (semi-supervised learning for example).