Artificial Intelligence (AI) is one of the most active and quickly developing fields of computer science and information systems, and has numerous applications in social science and engineering. The best way to study AI in this course is to learn by researching. In addition to a comprehensive introduction to a variety of AI subfields, this course will facilitate your exploration of state-of-the-art research and applications of AI, the production of your own ideas and visions, and discussions and sharing of some deep understandings. You will be asked to think about and communicate higher-level abstract ideas, including the concepts, strategies, principles, and algorithms of AI, rather than the technical details of implementation and programming. You will also be encouraged to test and evaluate ideas and algorithms through research-oriented studies involving software programming and/or exploring. You may be asked to read selected topics from the textbook, discuss your ideas and questions in the course conferences, explore programming and experimental work, and gather and study relevant research articles from important journals and conferences in the field of AI.
As a graduate-level course, this class focuses on advanced topics in AI, such as advanced search, reasoning under uncertainty, and machine learning. A general background of fundamental topics, such as informed search, logical agents, first-order logic (including its syntax, semantics, and inference), and knowledge representation, are also briefly introduced. This broad base is presented to help you to understand the advanced topics without having to take an undergraduate AI course (although it would certainly be an asset for this course). Those with less knowledge and experience in AI are invited to read the relevant fundamental topics in the textbook to gain an understanding of certain concepts and principles of advanced AI topics. Students who have taken an undergraduate AI course may skip the indicated Sections of the Study Guide. Units or Sections marked as "Optional" in the Syllabus and Study Guide are application-oriented topics, and are prepared for students who are interested in or familiar with them. You are encouraged to explore and use the topics or their associated applications when completing the TMAs and the Final Examination; however, no portion of the Final Exam will specifically focus on optional content.
[AIMA3ed]: Russell, S. J. and Norvig, P. (2010). Artificial intelligence: A modern approach (3rd edition). Upper Saddle River, NJ: Prentice-Hall. (ISBN 0-13-604295-7)
The textbook is referred to as AIMA3ed in the Study Guide, and is currently the required textbook for this course. AIMA2nd covers a great many concepts, theories, and algorithms from different subfields of AI, at different levels of difficulty; therefore, it is a good reference book that is capable of meeting the needs of students from different backgrounds.
Note: The Study Guide was originally designed with the 2nd edition of the textbook. This version has included minor changes made mainly to the Readings and Activities of each section so as to map the contents to the new places in the 3ed edition.
The Study Guide also lists many Required and Supplemental Readings, which reflect solid contributions and novel advancements to the field of artificial intelligence. These readings are provided to expand your knowledge and understanding, and to stimulate further interest in these topics. You will be able to access these readings, as well as a great many others that may be of interest to you, through AU Library's online service from journals such as Artificial Intelligence, Computational Intelligence, Journal of Artificial Intelligence Research, Machine Learning, IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Intelligent Systems, and conferences such as as International Joint Conferences on Artificial Intelligence (IJCAI), the Association for the Advancement of Artificial Intelligence (AAAI) Conference on Artificial Intelligence, and the International Conference on Machine Learning (ICML). To get a better feel for everyday research activities, you are asked to locate these papers for yourself, using the information provided in the Study Guide (journal title, volume and issue number, etc.), or the search tools provided by the Association of Computing Machinery (ACM), the Institute of Electrical and Electronics Engineers (IEEE), Elsevier, or Google Scholar.
The online resources provided by textbook's publisher (http://aima.cs.berkeley.edu/) will be helpful in learning, programming, and completing exercises and projects. You can download resources such as the source code for the algorithms listed in the textbook in different languages (mainly Java, Python, and Lisp). You are also encouraged to browse other AI-related websites (such as AAAI: https://aaai.org) and communities.
This course focuses on the concepts, principles, and techniques of AI, and thus we pay more attention to the ideas, methodology, and algorithms than we do to programming languages when we exercise implementations. For this reason, programming for experiments, assignments, and projects can be done by one or more of your chosen programming languages among a set of options (i.e., Java, Python, C++, Lisp, or Prolog), depending on your familiarity and how appropriate the language is to a specific technique and application. No matter which programming language you use, you must provide sufficient documentation and source code to allow the program to be compiled and executed under certain compilers and environments, as specified in the assignments or the course website.
When you complete this unit, you will be able to
Updated December 16 2021 by FST Course Production Staff