Scribd
Upload
35 views3 pages

AI Syllabus

Uploaded by

Dr. R. Gowri CIT
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
35 views3 pages

AI Syllabus

Uploaded by

Dr. R. Gowri CIT
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

Course Code L T P C

ARTIFICIAL INTELLIGENCE
CS4304 3 0 2 4

COURSE OBJECTIVES:
The main objectives of this course are to:
 Learn the fundamental AI approaches.
 Develop problem-solving skills relevant to AI.
 Explore different knowledge representation methods.
 Grasp planning approaches and apply it in decision-making.
 Understand the concept of reinforcement learning in real-time applications.

Course Description
This introductory course provides students with a foundational understanding of Artificial
Intelligence (AI).
Prerequisites
 Basic programming skills (preferably in Python).
 Familiarity with fundamental concepts in mathematics and computer science.

UNIT I: Introduction to Artificial Intelligence 9


Introduction: Foundations of AI – Intelligent agents: Environments, structure of agents – Problem-
solving: Searching for solutions, uninformed and informed search strategies, heuristic functions.
UNIT II: Advanced Search Strategies 9
Local Search Algorithms and Optimization Problems – Local search in Continuous Spaces –Global
optimization algorithms: Genetic Algorithms, Particle Swarm Optimization, Ant Colony
Optimization, Constraint Satisfaction Problems (CSP): Backtracking and local search for CSPs –
Adversarial Search: Games, Optimal decisions, alpha-beta pruning, imperfect real-time decisions,
stochastic games, partially observable games.
UNIT III: Knowledge Representation 9
Logical systems and Knowledge-Based systems – Representing knowledge using Propositional
Logic – Inference in Propositional Logic: Laws of Inference, Forward Chaining, Backward Chaining,
Resolution – Representing knowledge using First Order Logic –Inference in First Order Logic:
Unification, Forward Chaining, Backward Chaining.
UNIT IV: Planning and Quantifying Uncertainty 9
Classical Planning: Definition, Algorithms for Planning as State-Space Search, Planning Graphs –
Classical Planning Approaches – Planning and Acting: Time, Schedules, and Resources, Hierarchical
Planning – Planning and Acting in Nondeterministic Domains, Multi-agent Planning – Acting under
Uncertainty: Conditional Independence, Bayes Rule, Naive Bayes Classifier, Bayesian Belief Network
– Inference in Bayesian Belief Network – Making Decisions in Complex Environments: Markov
Decision Processes.
UNIT V: Reinforcement Learning and AI Applications 9
Introduction to Reinforcement Learning: Bandit algorithms, Policy Gradient, Markov Decision
Processes (MDPs) – Dynamic Programming & Temporal Difference (TD) Methods – Markov Chain
Monte Carlo (MCMC) Methods – Future Trends in AI: Quantum AI, Human-AI Collaboration,
Explainable AI, AI in Edge Computing, Artificial General Intelligence – Overview of AI applications in
various fields: Natural Language Processing (NLP), Computer Vision, Robotics, Business
Intelligence, Healthcare, Education, Finance, Manufacturing.
Course Format
Lectures and discussions, Hands-on coding exercises and projects, Online resources and tutorials.
Practical Exercises
Suggested exercises include implementing search strategies, solving constraint satisfaction
problems, developing game AI, and experimenting with basic reinforcement learning algorithms
using Python.
Assessments & Grading
Quizzes / Assignments, Project, Three Internal Assessments, Final Examination
COURSE OUTCOMES:
Upon completion of the course, the students will be able to:
CO1: Gain a foundational understanding of AI approaches.
CO2: Develop AI-related problem-solving skills via advance searching strategies.
CO3: Explore various knowledge representation methods.
CO4: Master planning techniques and apply them to decision-making scenarios.
CO5: Understand and implement reinforcement learning concepts in real-time applications.

TEXT BOOKS:
1. Russel, S. and Norvig, P., Artificial Intelligence – A Modern Approach, 4th Edition, Pearson
Education, 2021.
2. Sutton, R. S., & Barto, A. G., Reinforcement Learning: An Introduction, 2nd Edition, MIT Press,
2020.

REFERENCES:

1. Vinod Chandra. S.S, and Anand Hareendran, S., Artificial Intelligence and Machine Learning, PHI
Publishers, 2014.
2. Luger, G., Artificial Intelligence: Structures and Strategies for Complex Problem Solving, 6th
Edition, Pearson Education, 2008.
3. Nilsson, J., Artificial Intelligence: A New Synthesis, Elsevier Publishers, 1998.

YouTube Resources:
1. 3Blue1Brown: Mathematical foundations of AI algorithms.
2. Sentdex: Python programming tutorials for AI and machine learning.
3. Artificial Intelligence - All in One: Comprehensive tutorials on various AI topics.
4. Andrew Ng: Lectures on AI and machine learning concepts.
5. Google Developers: Tutorials and demos on AI tools and technologies.

TOTAL: 75 PERIODS

You might also like