Course Syllabus
Machine Learning: Linear Regression and Feature Selection, Analysis of variance for regression, Linear Classification, Support Vector Machines and Artificial Neural Networks, Bayesian Learning and Decision Trees, Evaluation Measures, Hypothesis Testing, Ensemble Methods, Clustering, Graphical Models, Learning Theory and Expectation Maximization, Introduction to Reinforcement Learning.
Introduction to Multi Agent Systems: Intelligent Agents, design of intelligent agents, reasoning agents (eg. AgentO), agents as reactive systems (eg. subsumption architecture), hybrid agents (eg. PRS), layered agents (eg. InteRRaP) a contemporary (Java-based) framework for programming agents (eg JADE Java Agent Development Environment).
Multi-Agent Systems: Classifying multi-agent interactions, cooperative versus non-competitive, zero-sum and other interactions, cooperation – the Prisoner’s dilemma and Axelrod’s experiments.
Interactions between self-interested agents: auctions & voting systems: negotiation.
Interactions between benevolent agents: cooperative distributed problem solving (CDPS), partial global planning; coherence and coordination;
Interaction languages and protocols: speech acts, KQML/KIF, the FIPA framework.
Case study, Coding and simulation works.