UCLan, CO3519: Artificial Intelligence, academic year 2021/22, semester 1 (Autumn 2021)

• Lecture: Tuesday, 14.00 - 15.00, digital (until further notice).
• Practical sessions: Friday, 14.00 - 15.00, CM019 (group #1); Friday, 15.00 - 16.00, CM034 (group #2).
• Office hours: Monday, 09.00 - 12.00, CM213.

Instructor: Martin Thomas Horsch (CM213).

Learning outcomes: Upon successful completion of this module, a student will be able to:

1. Explain the theoretical underpinnings of algorithms and techniques specific to artificial intelligence;
2. Critically evaluate the principles and algorithms of artificial intelligence;
3. Analyse and evaluate the theoretical foundations of artificial intelligence and computing;
4. Implement artificial intelligence algorithms.

Literature:

[RN] S. Russell, P. Norvig, Artificial Intelligence: A Modern Approach, 4th edn. (global), Harlow: Pearson (ISBN 978-1-29240113-3), 2021.
[McKinney] W. McKinney, Python for Data Analysis, 2nd edn., Sebastopol, CA: O'Reilly (ISBN 978-1-491-95766-0), 2018.

Glossary:

The glossary document introduces and defines selected key concepts from the domain.

Structure:

0. Introduction
   • Calendar week 40: Introductory meeting slides, How to set up Jupyter Notebook
   • G. T. Doran, "There's a S.M.A.R.T. way to write management's goals and objectives," Management Review 70(11): 35-36, 1981
   • Python Software Foundation, Python Tutorial, 2021
   • D. M. Wegner, "The mind's best trick: How we experience conscious will," Trends in Cognitive Sciences 7(2): 65-69, doi:10.1016/S1364-6613(03)00002-0, 2003
1. Optimization
   • Calendar week 41: Lecture slides, local optimization #1 (Jupyter notebook), tutorial document (discussion slides, discussion notebook)
   • Calendar week 42: Lecture slides, local optimization #2 (Jupyter notebook), multivariate optimization (Jupyter notebook), tutorial document (discussion slides)
   • Calendar week 43: Lecture slides, tutorial document (discussion)
   • RN, Sections 4.1, 4.2, and 15.4
2. Agents and decisions
   • Calendar week 44: Lecture slides, Pareto front (Jupyter notebook), tutorial document (discussion slides)
   • Calendar week 45: Lecture slides, multicriteria cost function (Jupyter notebook), Pareto front: Computation and visualization (Jupyter notebook, see remarks), tutorial document (discussion slides)
   • Calendar week 46: Lecture slides, agent function (Jupyter notebook), tutorial document (discussion slides, discussion notebook)
   • RN, Chapter 2, Sections 7.1 to 7.4, 15.1 to 15.3, 15.5, 19.3, and Chapters 28 and 29
   • R. Conte, "Rational, goal-oriented agents," doi:10.1007/978-1-4614-1800-9_158, in R. A. Meyers (ed.), Encyclopedia of Complexity and Systems Science, New York: Springer (ISBN 978-1-4614-1801-6), 2009
   • D. Dykeman, A. Hashibon, P. Klein, S. Belouettar, Guideline for Business Decision Support Systems (BDSS) for Materials Modelling, doi:10.5281/zenodo.4054008, Brussels: EMMC ASBL, 2020
   • A. M. Turing, "Computing machinery and intelligence," Mind 59(236): 433-460, doi:10.1093/mind/LIX.236.433, 1950
3. Modelling
   • Calendar week 47: Lecture slides, tutorial document
   • Calendar week 48: Lecture slides, Pareto front visualization #2 (Jupyter notebook, see remarks), linear regression #1 (Jupyter notebook)
   • Calendar week 49: Lecture slides, linear regression #2 (Jupyter notebook), tutorial document
   • Calendar week 50: Lecture slides, tutorial document
   • Coursework assessment specification (contributes 60% to the grade), shared doc for collecting ideas
   • RN, Sections 19.1, 19.2, and 19.4
   • Python statsmodels library for regression analysis

Grading:

• 60% from the coursework assessment;
• 40% from the final exam.

Index