Prerequisites topics
Probability, statistics, linear algebra
Contents:
- Artificial agents - nature and structure
- Search based problem-solving
- Uninformed search and heuristic search
- Local search
- Adversarial search and constraint satisfaction
- Propositional logic, first order logic and knowledge representation using semantic nets, taxonomy trees
- Uncertain knowledge representation: Bayesian nets, causal nets, inference, temporal models like HMM, dynamic Bayesian nets
- Planning: Heuristics, Hierarchical planning, planning in uncertain domains, scheduling
- Decision networks, sequential decision making, multi-agent decision making
- Learning from examples: regression and classification
- Deep learning models for computer vision and NLP
- Basics of Reinforcement learning
- Robotics - perception, planning and control, uncertain movements
- Humans and AI - impact, ethics, limits, laws
References
- Stuart Russell and Peter Norvig. Artificial Intelligence: A Modern Approach. Pearson, Fourth Edition, 2020.
- Richard E. Neapolitan and Xia Jiang. Artificial Intelligence with an Introduction to Machine Learning, CRC Press, Second Edition, 2018.
- Tom Mitchell. Machine Learning, McGraw Hill Education, First edition, 2017.
- Richard Duda, Peter Hart and David Stork. Pattern Classification, Wiley Interscience, Second Edition, 2007.