Artificial Intelligence is a major step forward in how computer system adapts, evolves and learns. It has widespread application in almost every industry and is considered to be a big technological shift, similar in scale to past events such as the industrial revolution, the computer age, and the smart phone revolution. This course will give an opportunity to gain expertise in one of the most fascinating and fastest growing areas of Computer Science through classroom program that covers fascinating and compelling healthcare, agriculture and many other areas. This course will give the students a rigorous, advanced and professional graduate-level foundation in Artificial Intelligence.
- Build intelligent agents for search and games.
- Learning optimization and inference algorithms for model learning.
- Solve AI problems through programming with Python.
- Design and develop programs for an agent to learn and act in a structured environment.
Duration : 45 hours
This course will give an opportunity to gain expertise in one of the most fascinating and fastest growing areas of Computer Science.
Module 1Introduction (3 Hours)
Concept of AI, history, current status, scope, agents, environments, Problem Formulations, Review of tree and graph structures, State space representation, Search graph and Search tree.
Module 2Search Algorithms (9 Hours)
Code ARTIFICIAL INTELLIGENCE L T P 3 - 2 Credits 4
Random search, Search with closed and open list, Depth first and Breadth first search, Heuristic search, Best first search, A* algorithm, Game Search.
Module 3Probabilistic Reasoning (12 Hours)
Probability, conditional probability, Bayes Rule, Bayesian Networks- representation, construction and inference, temporal model, hidden Markov model.
Module 4Markov Decision process (12 Hours)
MDP formulation, utility theory, utility functions, value iteration, policy iteration and partially observable MDPs.
Module 5Reinforcement Learning (9 Hours)
Passive reinforcement learning, direct utility estimation, adaptive dynamic programming, temporal difference learning, active reinforcement learning- Q learning.
List of Practicals
- Write a programme to conduct uninformed and informed search.
- Write a programme to conduct game search.
- Write a programme to construct a Bayesian network from given data.
- Write a programme to infer from the Bayesian network.
- Write a programme to run value and policy iteration in a grid world.
- Write a programme to do reinforcement learning in a grid world.
- Mini Project work.