COMP 3711: Applied Artificial Intelligence
Students investigate non-deterministic computer algorithms that are used in wide application areas but cannot be written in pseudo programming languages. Non-deterministic algorithms have been known as topics of machine learning or artificial intelligence. Students are introduced to the use of classical artificial intelligence techniques and soft computing techniques. Classical artificial intelligence techniques include knowledge representation, heuristic algorithms, rule-based systems, and probabilistic reasoning. Soft computing techniques include fuzzy systems, neural networks, and genetic algorithms. Students will be able to connect and apply a depth and breadth of knowledge in Artificial Intelligence to a wide domain of complex problems beyond Computing Science.
Learning outcomes
- Critically examine the major areas and challenges of AI, and consider how the field is evolving.
- Integrate knowledge from diverse stakeholder fields to identify problems that are amenable to solution by AI methods, and demonstrate appropriate AI methods best suited to solving a given problem.
- Formalize a given problem in the language/framework of different AI methods.
- Implement basic AI algorithms to approximate and represent phenomenon and solve complex contemporary problems.
- Design and implement software to experiment with various AI concepts and analyze results.
Note: Knowledge of a programming language, such as Java, will be helpful.
Course topics
- Intelligent agents
- Knowledge representation
- Classical searching
- Advanced searching
- Genetic algorithms
- Knowledge representation and automatic reasoning
- Machine learning and neural networks
- Probabilistic reasoning
- Fuzzy reasoning
Required text and materials
Students are responsible for purchasing the required materials on their own:
- Russell, S. & Norvig, P. (2021). Artificial Intelligence: A Modern Approach (4th ed.). Pearson.
Type: Textbook. ISBN: 9780134610993 / 9780134671932
Note: This item can be purchased directly from the following link.
- Poole, D. L., & Mackworth, A. K. (2017). Artificial intelligence: Foundations of computational agents (2nd ed.). Cambridge, United Kingdom: Cambridge University Press.
Note: Available for free at the following link
Optional materials
Professional Organizations and Publications
For their own professional development, students may want to follow and/or subscribe to the following two professional networks.
- IEEE Computational Intelligence Society
- IEEE Transactions on Computational Intelligence and AI in Games (Journal)
Demonstration Tools
These tools are helpful for learning and exploring concepts in artificial intelligence. You will find these helpful at various points throughout the course.
Assessments
Please be aware that should your course have a final exam, you are responsible for the fee to the online proctoring service, ProctorU, or to the in-person approved Testing Centre. Please contact exams@tru.ca with any questions about this.
To successfully complete this course, students must achieve a passing grade of 50% or higher on the overall course, and 50% or higher on the final mandatory exam.
| Assignment 1: Environment Simulator | 5% |
| Assignment 2: A* Search | 8% |
| Assignment 3: Beyond Classical Search | 10% |
| Assignment 4: Problematic Reasoning and Knowledge Representation | 15% |
| Assignment 5: Machine Learning | 12% |
| Mandatory Final Exam | 50% |
| Total | 100% |
Open Learning Faculty Member Information
An Open Learning Faculty Member is available to assist students. Students will receive the necessary contact information at the start of the course.
