This module covers the basic principles of machine learning and the kinds of problems that can be solved by such techniques. Students will learn about the philosophy of AI, how knowledge is represented and algorithms to search state spaces. The module also provides an introduction to both machine learning and biologically inspired computation.
Total contact hours: 28
Private study hours:122
Total study hours: 150
Main assessment methods
A1 – Practical assignment (25%)
A2 – Practical assignment (25%)
2 hour unseen written examination (50%)
The University is committed to ensuring that core reading materials are in accessible electronic format in line with the Kent Inclusive Practices.
The most up to date reading list for each module can be found on the university's reading list pages.
S.J. Russell & P. Norvig, "Artificial Intelligence: a modern approach", 4th Edition. Pearson, 2020. (main textbook)
S. Pinker. "How the Mind Works", W.W. Norton & Company, 1999.
A. Cawsey, "The Essence of Artificial Intelligence", Prentice-Hall, 1998.
P. Bentley. "Digital Biology: How Nature Is Transforming Our Technology and Our Lives", Simon & Schuster, 2007.
S. Marsland, "Machine Learning: An Algorithmic Perspective", CRC Press, Taylor and Francis, 2nd Edition, 2014.
E. K. Burke & G. Kendall, "Search Methodologies: Introductory Tutorials in Optimization and Decision Support Techniques", 2nd Edition, Springer, 2014
S. Haykin, "Neural Networks and Learning Machines", 3rd Edition. Pearson, 2009
R.L. Haupt & S.E. Haupt, “Practical Genetic Algorithms”, 2nd edition, Wiley, 2004.
On successfully completing the module students will be able to:
1. Demonstrate knowledge and understanding of the motivation for designing intelligent machines, their implications and associated philosophical issues, such as the nature of intelligence and learning.
2. Demonstrate systematic understanding, critical awareness and application of the main kinds of state-space search algorithms, considering their strengths and limitations.
3. Understand and explain the main concepts and principles associated with different kinds of knowledge representation, such as logic, case-based representations, and subsymbolic/connectionist representations.
4. Understand and explain the differences between the major kinds of machine learning problems – namely supervised learning, unsupervised learning and reinforcement learning – and describe and implement the fundamental ideas of algorithms for solving those problems.
5. Demonstrate mastery of the main concepts and principles of major kinds of biologically-inspired algorithms, and understand the implementation and evaluation of one such technique.
6. Demonstrate comprehensive understanding of how various intelligent-system techniques have been used in the context of several case studies, and critically compare different techniques in the context of those case studies.
University of Kent makes every effort to ensure that module information is accurate for the relevant academic session and to provide educational services as described. However, courses, services and other matters may be subject to change. Please read our full disclaimer.
