Course content

This course is a continuation of TDT4136 Introduction to Artificial Intelligence and TDT4172 Introduction to Machine Learning. The three main ways of reasoning (rule-based, model-based, and case-based), will be discussed, with most focus given to model-based reasoning. In particular, we work with reasoning based with uncertain and/or partly missing information. The reasoning frameworks that are most prominent in this part of the course are Bayesian networks and decision graphs.Thereafter, we discuss modern techniques for machine learning.

Learning outcome

Knowledge:

• General principles for artificial intelligence (AI)
• Efficient representation of uncertain knowledge
• Decision making principles
• Learning/adaptive systems.

Skills:

• Assess different frameworks for AI in given contexts
• Build systems that realises aspects of intelligent behaviour in computer systems.

General competence:

• Know AI's basis taken from mathematics, logic and cognitive sciences.

Learning methods and activities

Lectures, self study and exercises.

Compulsory assignments

• Mandatory assignments

Recommended previous knowledge

• TDT4136 Introduction to Artificial Intelligence, or equivalent.
• TMA4240 Statistics or similar
• TDT4172 Introduction to Machine Learning or similar
• Programming experience, e.g., TDT4109 - Information Technology, Introduction

Course materials

• Stuart Russel, Peter Norvig: Artificial Intelligence. A Modern Approach, Fourth Edition, Pearson, 2020.
• Ian Goodfellow and Yoshua Bengio and Aaron Courville: Deep Learning, MIT Press, 2016.

Any additional material will be distributed through the course's webpage.

Credit reductions