Artificial Intelligence, Reasoning & Decision Making

Learning Outcomes:

• Understanding fundamental concepts of AI agents, environments, and decision making
• Applying probability theory and Bayesian reasoning to AI problems
• Constructing and reasoning with Bayesian networks
• Implementing inference algorithms like variable elimination and sampling methods
• Analyzing sequential decision problems using Markov Decision Processes
• Solving MDPs through techniques like value iteration and policy iteration
• Exploring game theory concepts including Nash equilibria and Pareto optimality
• Developing argumentation frameworks and evaluating argument acceptability
• Implementing clustering algorithms like k-means and hierarchical clustering
• Applying dimensionality reduction techniques such as PCA
• Designing agent communication languages and dialogue protocols
• Examining ethical considerations in AI development and deployment
• Evaluating different AI approaches for reasoning under uncertainty
• Implementing search algorithms for problem solving in AI
• Understanding knowledge representation techniques in AI systems

Skills for module:

Artificial Intelligence

Machine Learning

Intelligent Agents

Probability

Statistics

Mathematics

Algorithms

Data Structures

Problem Solving

Logics

Data Science

Critical Thinking

Time Management