Artificial Intelligence

Artificial Intelligence course focuses on the development of algorithms and statistical models.

Course Objectives

  • To learn the difference between optimal reasoning vs human like reasoning.
  • To understand the notions of state space representation, exhaustive search, heuristic search.
  • To learn different knowledge representation techniques.
  • To understand the applications of AI like Game Playing and Expert Systems.
  • To introduce the concept of Machine Learning.

Course Syllabus

UNIT 1

Introduction: History, Intelligent Systems, Foundations of AI, Subareas of AI & Applications.

Intelligent Agents: Agents and Environment, Structure of Agents

Solving Problems by Searching:

Uninformed Search Strategies – Depth-first search – Breadth-first search – Uniform-cost search

Informed (Heuristic) Search Strategies – Heuristic Functions – Greedy best-first search – A* search

Hill climbing search

UNIT 2

Adversarial Search: Optimal Decisions in Games – MiniMax Algorithm, Alpha-Beta Pruning

Constraint Satisfaction Problems

Bayesian Learning: Bayes Theorem and Concept Learning – Maximum Likelihood and Least square Error Hypothesis – Bayes Optimal Classifier – Naïve Bayes Classifier

Minimum Description Length Principle – Gibbs Algorithm – Bayesian Belief Networks – EM Algorithm

UNIT 3

Introduction to Machine Learning: Examples of Machine Learning Applications – Learning Associations -Classification – Regression – Unsupervised Learning – Reinforcement Learning

Supervised Learning: Learning a Class from Examples – Vapnik-Chervonenkis Dimension – Probably Approximately Correct Learning – Noise – Learning Multiple Classes – Regression – Model Selection and Generalization – Dimensions of a Supervised Machine Learning Algorithm

UNIT 4

Artificial Neural Networks: Introduction, Appropriate problems for NN learning, Perceptrons, Multilayer Networks and Backpropagation Algorithm, Remarks on Backpropagation Algorithm, An example: Face recognition, Advanced topics of ANN-Error functions, Recurrent Networks

UNIT 5

Decision Trees: Introduction – Univariate Trees – Classification Trees – Regression Trees – Pruning – Rule Extraction from Trees – Learning Rules from Data – Multivariate Trees – Problems on Decision Tree

Reinforcement Learning: Introduction – The Learning Task – Q-Learning – Non deterministic rewards and actions – Temporal difference Learning – Generalizing from examples – Relationship to dynamic programming

Text Books

Saroj Kaushik, Artificial Intelligence, Cengage Learning, 2011.

Reference Books

  • Rich, Knight, Nair: Artificial Intelligence, Tata McGraw Hill, 3rd Edition, 2009.
  • Eugene Charniak, Introduction to Artificial Intelligence, Pearson, 2007
  • Dan W.Patterson, Introduction to Artificial Intelligence and Expert Systems, PHI, 1990.
  • George Fluger, Artificial Intelligence, 5th Edition, Pearson.

Online Resources

  • http://www.vssut.ac.in/lecture_notes/lecture1428643004.pdf
  • http://nptel.ac.in/courses/106105077/
  • https://onlinecourses.nptel.ac.in/noc18_cs18/preview
  • https://www.edx.org/course/artificial-intelligence-ai-columbiax-csmm-101x-4

Course Outcomes

After completion of the course, students will be able to:

  • Understand the basics of AI and to formulate efficient problem space and select a search algorithm for a problem.
  • Apply AI techniques to solve problems related to Game Playing, Expert Systems.
  • Understand and apply Logic programming in problem solving.
  • Represent knowledge using appropriate techniques.
  • Interpretation of probabilistic and logical reasoning in knowledge base.
  • Understand the concepts of machine learning.

For Fundamentals of Blockchain Technology course CLICK HERE

For Embedded System Design course CLICK HERE

For other courses CLICK HERE

If you found this page interesting and helpful, don’t forget to share it with your friends.