5042.22 - Introduction to Artificial Intelligence


Course number
5042.22
Title
Introduction to Artificial Intelligence
ECTS
7.5
Prerequisites
Discrete Mathematics (7.5 ECTS), Algorithms and data structures (7.5 ECTS), Introductory programming with Python (7.5 ECTS)
Purpose
The objective of this course is to introduce the basic ideas and intuition behind the design of intelligent computer systems. A specific emphasis will be on the statistical and decision-theoretic modelling paradigm.
Content
What is AI? The Foundation of Artificial Intelligence. Planning agents. Uninformed searching strategies. Informed/Heuristic search strategies: A*, Greedy search. Nondeterminism and partially observable. Adversarial Search: Game trees, Minimax. Pruning techniques. Solving Markov decision processes. Bayesian network representation and assumptions. Inferences and sampling techniques. Supervised learning. Neural networks. Convolutional neural networks. Applications and limitations of neural networks. Reinforcement Learning, Model-based learning. Model-free learning. Q-learning.
Learning and teaching approaches
Lectures, exercises, home assignments, self-studies and group work.
Learning outcomes
By the end of the course, the student is expected to be able to: - Explain, apply, and implement uninformed and informed search techniques to solve AI problems. - Explain, apply, and implement artificial intelligence search techniques in games. - Design, implement, benchmark, and analyse search heuristics and game evaluation functions. - Explain, design, and implement intelligent systems that draw inferences in uncertain environments and optimise actions for arbitrary reward structures. - Design, and develop an autonomous agent that efficiently makes decisions in fully informed, partially observable, and adversarial settings. - Correctly identify the relevant AI technique for solving a given problem. - Explain the strengths and weaknesses of different AI techniques in search and planning, probabilistic reasoning, and machine learning.
Assessment method
A 4-hour written exam. All three mandatory assignments must be passed to be eligible for the examination and re-examination.
Examination
External
Marking scale
7-
Bibliography
A Modern Approach (Pearson Education) - Stuard J. Russell and Peter Norvig Paperback: 1168 pages Pearson Education; 4th edition – 2021 Language: English ISBN-10: 1292401133 ISBN-13: 978-1292401133 https://www.amazon.co.uk/Artificial-Intelligence-Modern-Approach-Global/dp/1292401133
Contact
Jákup Odssonur Svøðstein