COMP3308: Introduction to Artificial Intelligence
Gained practical AI skills across search, games, and machine learning—plus the judgement to know when they work.
Learning Outcomes
- Search & Game Algorithms: Formulated problem spaces; implemented uninformed search, minimax, alpha-beta pruning.
- Machine Learning Fundamentals: Applied supervised / unsupervised and probabilistic methods; evaluated strengths & limits.
- AI Implementation & Evaluation: Designed and tested AI algorithms on varied problems.
- Communication & Reflection: Presented AI concepts and project outcomes clearly in writing and talks.
- AI Perspectives: Discussed real-world achievements, ethics, and CS relationships.
Takeaways
This course was dense, almost overwhelming at times, but ultimately rewarding. It brought together a wide spectrum of AI foundations: search algorithms such as minimax, alpha-beta pruning, and A*; probabilistic reasoning with Bayesian networks; classical machine learning methods like SVMs, k-nearest neighbors, and decision trees; and introductory neural networks and deep learning. The breadth was enormous, demanding not only technical understanding but also the ability to integrate and prioritize knowledge. What I gained was less about memorizing every algorithm and more about developing judgment—knowing when each approach is appropriate, and understanding its limitations. The unit also highlighted the importance of stepping back and seeing the bigger picture: how AI methods connect across games, classification, recommendation systems, and real-world decision-making. I left with a strong conceptual foundation, a sense of direction for further exploration, and the confidence to approach complex AI problems with both rigor and perspective.