Scribd
Upload
23 views

AI&ML

This document provides information about the course "Artificial Intelligence with Machine Learning". It is a 4 credit course offered in classroom/blended mode. It introduces fundamental machine learning methods and enables computers to learn, plan and solve problems autonomously. The course covers theoretical foundations of supervised and unsupervised learning, artificial neural networks, and instance-based learning. It aims to help students understand various AI algorithms, knowledge representations, and the importance of planning to solve AI problems. The syllabus is divided into 5 units covering key topics like search techniques, first-order logic, classical planning, machine learning models, and neural networks.

Uploaded by

PrasadaRao
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
23 views

AI&ML

This document provides information about the course "Artificial Intelligence with Machine Learning". It is a 4 credit course offered in classroom/blended mode. It introduces fundamental machine learning methods and enables computers to learn, plan and solve problems autonomously. The course covers theoretical foundations of supervised and unsupervised learning, artificial neural networks, and instance-based learning. It aims to help students understand various AI algorithms, knowledge representations, and the importance of planning to solve AI problems. The syllabus is divided into 5 units covering key topics like search techniques, first-order logic, classical planning, machine learning models, and neural networks.

Uploaded by

PrasadaRao
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

Course Code 20CS4T2 Course Delivery Method Class Room / Blended Mode

Credits 4 CIA Marks 30


No. of Lecture Hours / Week 4 Semester End Exam Marks 70
Total Number of Lecture 60 Total Marks 100
Hours
Year of Introduction :2018 Year of Offering:2021 Year of Revision:2021-22 Percentage of Revision:10%

Course Objective:This course focuses on How to realize the Intelligent Human Behaviors on a
Computer and introduces the Fundamental Methods at the core of modern Machine Learning, It
enables a computer to Learn, Plan, and Solve problems Autonomously, It covers Theoretical
Foundations as well as Essential Concepts in Supervised and Unsupervised Learning,ANN, Instance
Based Learning.

Course Outcomes:

At the end of this course, students will be able to:


CO1 :Identify problems that are amenable to AI Techniques and analyse Search Techniques to solve
those problems.
CO2 :Understand Representation Languages like First Order Logic.
CO3 :Formalize and implement different AI Algorithms, various Knowledge Representations and
identify the importance of planning to solve AI Problems.
CO4 :Understand about basics of Machine Learning and Conceptual Learning.
CO5 :Acquire knowledge about ANN and Instance Based Learning.

Syllabus

Course Details

Unit Learning Units Lecture Hours


I Introduction: What Is AI? The Foundations of Artificial Intelligence, The
History of Artificial Intelligence.
Solving Problems by Searching: Problem-Solving Agents, Example 10
Problems, Searching for Solutions, Uninformed Search Strategies, Informed
(Heuristic) Search Strategies, Heuristic Functions.
First-Order Logic: Syntax and Semantics of First-Order Logic, Using First-
Order Logic, Knowledge Engineering in First-Order Logic.
II Inference in First-Order Logic: Propositional vs. First-Order Inference, 10
Unification and Lifting, Forward Chaining, Backward Chaining, Resolution.

Classical Planning: Definition of Classical Planning ,Algorithms for Planning


as State-Space Search, Planning Graphs, Other Classical Planning Approaches,
III Analysis of Planning Approaches. 15
Knowledge Representation: Ontological Engineering, Categories and Objects
Events, Mental Events and Mental Objects.
Learning from Examples: Forms of Learning, Supervised Learning, Learning
Decision Trees, Evaluating and Choosing the Best Hypothesis, The Theory of
Learning, Regression and Classification with Linear Models.
IV Reinforcement Learning: Introduction, Passive Reinforcement Learning,
15
Active Reinforcement Learning, Generalization in Reinforcement Learning,
Policy Search, Applications of Reinforcement Learning.
Artificial Neural Networks: Neural Network Representation, Appropriate
Problems for Neural Network Learning, Perceptrons, Multilayer Networks and
the Backpropagation Algorithm, Remarks on the Backpropagation Algorithm,
V Recurrent Networks, Dynamically Modifying Network Structure.
10
Instance-Based Learning: Introduction, K-Nearest Neighbour Learning,
Radial Basis Functions, Case-Based Reasoning.

Prescribed Text Book


Author Title Publisher
1 Stuart J. Russell and Artificial Intelligence A Modern Prentice Hall, Third edition,2010
Peter Norvig Approach 1.1,1.2,1.3,3.1,3.2,3.3,3.4,3.5,3.6,
8.2,8.3,8.4,9.1,9.2,9.3,9.4,9.5,
10.1,10.2,10.3,10.4,10.5,12.1,12.2,
12.3,12.4,18.1,18.2,18.3,18.4,18.5,
21.1, 21.2, 21.3, 21.4, 21.5, 21.6
2 Tom.M. Mitchell Machine Learning TMH (2013) 4.2,4.3,4.4,4.5,4.6,4.7,
4.8,8.1,8.2,8.4,8.5.

Reference Text Book


Author Title Publisher
1 Winston. P.H Artificial Intelligence Addison Wesley (1993)

2 Peter Flach Machine Learning The Art Cambridge PearsonEducation (2007),


and Science of Algorithms University Third Edition.
that Make Sense of Data Press
3 Elaine Rich& Kevin Artificial Intelligence TMH (1991)
Knight

Course has focus on :Foundation, Employability


Websites of Interest :
1. https://www.cs.utexas.edu/~mooney/cs343/
2. https://www.cin.ufpe.br/~cavmj/Machine%20-%20Learning%20-%20Tom%20Mitchell.pdf
3. https://www.researchgate.net/publication/
337704931_Concept_of_Artificial_Intelligence_its_Impact_and_Emerging_Trends
4. https://machinelearningmastery.com/basic-concepts-in-machine-learning/

A.G & S.G Siddhartha Degree College of Arts & Science, Vuyyuru – 521165.
(An Autonomous College in the jurisdiction of Krishna University)
M.Sc., (Computer Science) Programme – IV Semester

Course Code: 20CS4T2 Title: ARTIFICIAL INTELLIGENCE WITH MACHINE LEARNING


Time: 3Hours

SECTION-A Max.Marks:70

1. Answer ALL questions


a) Define Artificial Intelligence (AI).
b) Define Rational Agent
c) Define Back Propagation
d) Define Vector Machines
e) What is K-Means Cluster?
f) Define Kernal Methods.
g) What is Polynomial regression?
h) Define Kernal Estimator
i) What is Q Learning?
j) What is Fixed Combination Rules

SECTION-B Answer Five Questions Choosing One Question from Each Unit.
All Questions Carry Equal Marks. (5×10=50Marks)
2 a) What is AI? Discuss the Heuristic Search Techniques for solving problems.(BTL1)
(or)
b) Discuss Problem Solving Agents with Examples. (BTL6)
3 a) Explain the Syntax and Semantics of First Order Logic.(BTL2)

(or)
b) Demonstrate the concept of resolution with an example.(BTL2)
4 a) Explain how to design algorithms for Planning as State Space Search. (BTL2)

(or)
b) Discuss On to logical Engineering in Knowledge Representation.(BTL6)
5 a) Describe Learning Decision Trees and Evaluating and Choosing Best Hypothesis.(BTL2)

(or)
b) Explain Policy Search and Applications of Reinforcement Learning.(BTL2)
6 a) Discuss the Back Propagation Algorithm, Remarks on the Back Propagation Algorithm.(BTL6)
(or)
b) How does K-Nearest Neighbour Learning help in Instance Based Learning and also state the
Importance of Radial Basis Functions. (BTL1)

You might also like