Artificial Intelligence

ELECTIVE GROUP : I CREDITS: 03

SEMESTER : 5 L:T:P – 3:0:0

IA/UE : 30/70 CONTACT HRS/WEEK : 03

Course Objective:

1 To understand the basic concepts of Artificial Intelligence, terminologies related to AI in

present business world.
2 To understand the application of ANN, Deep Learning, NLP in Artificial Intelligence.

3 To understand the application and importance of Computer Vision in Artificial Intelligence.

4 To understand the different applications and techniques involved in AI for real time
scenarios.

Course Outcomes:

CO
1 Define and outline the basics, importance and application of Artificial Intelligence.

CO Apply the technique of Artificial Neural Network in finding out the importance of predictable
2 power in AI.

CO Describe the application of Deep Learning in Artificial Intelligence.

3

CO Demonstrate to calculate, test and tune the assumptions of Artificial Intelligence

4 techniques and interpret their parameters for the model building.
CO Employ and use Natural language processing techniques and understand its importance in
5 sentimental analysis.

CO Employ computer vision techniques to understand the importance of Artificial

6 Intelligence in real time imaging process.

CO-PO MAPPING

Course Outcomes – Program Outcome Mapping ( H/M/L : 3/2/1)

PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2

CO1 3 1 2 1 1 1 1

CO2 3 2 2 1 1 1

CO3 2 2 3 2 1 1 1

CO4 3 3 3 2 2 2 1 2 1

CO5 3 3 3 3 3 2 1 1 2 2

CO6 2 3 3 3 2 2 1 1 2 2

total
 16 16 16 12 8 6 3 4 9 7

UNIT- I [9 HOURS]

Introduction to AI: What is AI? , Thinking humanly, Acting rationally, The Foundations of Artificial Intelligence,
The History of Artificial Intelligence, The gestation of artificial intelligence, AI becomes an industry, Knowledge-
based systems, The return of neural networks, The State of the Art, Intelligent Agents, How Agents Should Act,
Structure of Intelligent Agents, Simple reflex agents, Goal-based agents, Utility-based agents , Environments,
Environment programs.

UNIT- II [9 HOURS]

Problem-solving : Solving Problems by Searching, Problem-Solving Agents, Formulating Problems, Well-

defined problems and solutions, Measuring problem-solving performance, Toy problems, Searching for
Solutions, Search Strategies, Avoiding Repeated States, Constraint Satisfaction Search, Informed Search
Methods, Best-First Search, Heuristic Functions, Memory Bounded Search, Iterative Improvement Algorithms,
Applications in constraint satisfaction problems.

UNIT- III [9 HOURS]

Knowledge and reasoning : A Knowledge-Based Agent, Representation, Reasoning, and Logic, Prepositional
Logic, An Agent for the Wumpus World, Problems with the propositional agent, First-Order Logic, Syntax and
Semantics, Extensions and Notational Variations, Using First-Order Logic, A Simple Reflex Agent, Deducing
Hidden Properties of the World, Toward a Goal-Based Agent, Building a Knowledge Base, Knowledge
Engineering, General Ontology, The Grocery Shopping World, Inference Rules Involving Quantifiers,
Generalized Modus Ponens, Forward and Backward Chaining, Completeness, Resolution: A Complete
Inference Procedure, Completeness of resolution.

UNIT- IV [9 HOURS]

Acting logically : A Simple Planning Agent, From Problem Solving to Planning, Planning in Situation Calculus,
Basic Representations for Planning, A Partial-Order Planning Algorithm, Planning with Partially Instantiated
Operators, Knowledge Engineering for Planning, Practical Planners, Hierarchical Decomposition, Analysis of
Hierarchical Decomposition, More Expressive Operator Descriptions, Resource Constraints, Planning and
Acting, Conditional Planning, A Simple Re-planning Agent, Fully Integrated Planning and Execution

UNIT- V [9 HOURS]

Generalized Models : A General Model of Learning Agents, Components of the performance element,
Representation of the components, Inductive Learning, Learning Decision Trees, Using Information Theory,
Learning General Logical Descriptions, Computational Learning Theory, Learning in Neural and Belief
Networks, Neural Networks, Perceptrons, Multilayer Feed-Forward Networks, Applications of Neural Networks,
Bayesian Methods for Learning Belief Networks, Reinforcement Learning, Passive Learning in a Known
Environment, Passive Learning in an Unknown Environment, Generalization in Reinforcement Learning,
Genetic Algorithms and Evolutionary Programming, Explanation-Based Learning, Learning Using Relevance
Information, Inductive Logic Programming.

Text Book:

1. Artificial Intelligence, A Modern Approach, Stuart J. Russell and Peter Norvig,Pearson, 3rdedition, 2016.
 2. principles of artificial neural networks ,danielgraupe university of lllinois, chicago, usa, 2nd edition, 2007.

Reference Book:

1. Artificial Intelligence (Sie) (English, Paperback, Knight Kevin),3rd edition, 2017.

2. Artificial Intelligence: An Essential Beginner’s Guide to AI, Neil Wilkins,2019.