Course Description
This course provides an overview of methods, history, and impact of AI. It covers problem solving, heuristic search, planning, game playing, reasoning with propositional and predicate logic, reasoning under uncertainty, machine learning, applications (natural language processing, vision, robotics, as time permits). Students will solve a variety of AI problems using Python. Includes a discussion of the role of AI technology in society.
Course Objectives
Artificial intelligence studies how computers can be made to behave intelligently. In this course we will cover theoretical and practical approaches to AI, with topics to include search, logic, knowledge representation, uncertainty, and different aspects of the performance of AI techniques.
Key Concepts
- AI Fundamentals: Explain different types of learning in AI and their real-world applications.
- Search & Problem Solving: Implement basic search algorithms to solve puzzles and pathfinding tasks.
- Learning from Data: Train and evaluate ML models (Decision Trees, SVMs) for simple datasets.
- Neural Networks: Build and test basic neural networks (MLP, CNN) for recognition tasks.
- Reinforcement Learning: Simulate simple agents that learn through trial and error.
- AI & Society: Recognize ethical issues (bias, privacy) and discuss their impact.
Learning Outcomes
- Students understand and explain the core principles of AI.
- Students can implement classical search algorithms and basic problem solvers.
- Students can apply machine learning methods (decision trees, SVM, Bayesian models).
- Students can build and train simple neural networks.
- Students are able to discuss the ethical and societal impact of AI.
Recommended Textbooks
Stuart Russell and Peter Norvig, Artificial Intelligence: A Modern Approach, 4th edition.