Artificial Intelligence II

Planning: Search based planning, logic based planning, planning graphs, resource-constrained time scheduling, hierarchical task networks, planning in non-deterministic fields, multi-agent planning. Action under uncertainty: Bayes networks, probabilistic reasoning, approximate reasoning, reasoning with Markov chains, fuzzy logic, temporal model reasoning, hidden Markov models, Kalman filters, dynamic Bayes networks, applications in speech recognition. Decision making: Utility theory, multimodal utility functions, decision networks, expert systems, game theory. Machine learning: Decision trees, inductive learning, explanation based learning, inductive logic programming, statistical learning methods, naive Bayes models, EM algorithm, Gauss learning, instance learning, kernel models and machines, neural networks, reinforcement learning. Communication: Formal grammars and languages, syntactic analysis, semantic interpretation, DCG grammars, ambiguity resolution, text understanding, stochastic language models, PCFG grammars, information extraction, machine translation. Perception and action: Machine vision, object identification from images, robotic perception, location and mapping, robotic sensors and actuators, movement planning, robotic software architectures.

Objectives

-

Prerequisites

Artificial Intelligence I

Syllabus

Planning: Search based planning, logic based planning, planning graphs, resource-constrained time scheduling, hierarchical task networks, planning in non-deterministic fields, multi-agent planning. Action under uncertainty: Bayes networks, probabilistic reasoning, approximate reasoning, reasoning with Markov chains, fuzzy logic, temporal model reasoning, hidden Markov models, Kalman filters, dynamic Bayes networks, applications in speech recognition. Decision making: Utility theory, multimodal utility functions, decision networks, expert systems, game theory. Machine learning: Decision trees, inductive learning, explanation based learning, inductive logic programming, statistical learning methods, naive Bayes models, EM algorithm, Gauss learning, instance learning, kernel models and machines, neural networks, reinforcement learning. Communication: Formal grammars and languages, syntactic analysis, semantic interpretation, DCG grammars, ambiguity resolution, text understanding, stochastic language models, PCFG grammars, information extraction, machine translation. Perception and action: Machine vision, object identification from images, robotic perception, location and mapping, robotic sensors and actuators, movement planning, robotic software architectures.