Gujarat Technological University: Rationale

Download as pdf or txt
Download as pdf or txt
You are on page 1of 3

GUJARAT TECHNOLOGICAL UNIVERSITY

Bachelor of Engineering
Subject Code: 3170924
Semester – VII
Subject Name: AI and Machine learning

Type of course: Professional Elective Course

Prerequisite: Linear Algebra, Probability

Rationale:

Artificial Intelligence is now a day used in nontechnical and technical fields. In every branch of engineering
the AI has been used and Electrical engineering is also one of them infect, the use of AI technique in Electrical
engineering is inevitable. The branches of electrical Engineering like Electrical Power Systems, Power
Electronics and Smart grid technologies are some of them. The course is aimed to provide exposure about the
fundamentals of AI techniques and use of some basic machine learning algorithms to be used in electrical
engineering and in other branches of electrical engineering too; the commonly used AI techniques from the
application viewpoints will be covered in the this course.

Teaching and Examination Scheme:


Teaching Scheme Credits Examination Marks Total
L T P C Theory Marks Practical Marks Marks
ESE PA ESE PA
(E) (M) Viva (V) (I)
3 0 0 3 70 30 0 0 100

Contents:

Sr. No. Content Total


Hrs
1 Introduction: Scope of the Course, Introduction to AI, Brief review of History 03
of AI, Related fields
2 Introduction to Artificial Neural Networks: Biological Neurons and 07
Biological Neural Networks, Artificial Neural Networks, Activation Functions,
Perceptron NN, Multilayer Perceptron NN, Back-propagation Neural Networks,
Training Methods, Basic definition of supervised and unsupervised Learning.

3 Introduction to Machine Learning: Introduction (Different Types of Learning) 02


Hypothesis Space, Inductive Bias, Evaluation and Cross Validation

4 Main Algorithms used in Machine Learning: Linear Regression, Decision 08


Trees, Learning Decision Trees, K-nearest Neighbour, Collaborative Filtering,
Overfitting, Dimensionality Reduction Technique :Feature Selection, Feature
Extraction
5 Logistic Regression and Support Vector Machine: 06
Logistic Regression, Introduction to Support Vector Machine, The Dual
Formation, Maximum Margin with Noise, Nonlinear SVM and Kernel Function,
SVM: Solution to the Dual Problem
6 Advanced Learning methods and Clustering: Introduction to Clustering, K- 06
means Clustering, Agglomerative Hierarchical Clustering, Basics of Semi-
Supervised and Reinforcement Learning, Introduction to Deep Learning

Page 1 of 3
w.e.f. AY 2018-19
GUJARAT TECHNOLOGICAL UNIVERSITY
Bachelor of Engineering
Subject Code: 3170924
7 . Fuzzy Logic Introduction , Conventional set vs fuzzy set, Operations of fuzzy 06
set , Membership function, Fuzzy rules, Fuzzy inference, De-fuzzification,,
Application for control
8 Genetic algorithm Introduction, Comparison with traditional optimisation 07
Technique, Steps for GA, reproduction, Crossover, Mutation, Termination
parameter of GA, Application.
Suggested Specification table with Marks (Theory): (For BE only)

Distribution of Theory Marks

R Level U Level A Level N Level E Level C Level


10 25 30 15 10 10

Legends: R: Remembrance; U: Understanding; A: Application, N: Analyze and E: Evaluate C: Create


and above Levels (Revised Bloom’s Taxonomy)

Note: This specification table shall be treated as a general guideline for students and teachers. The actual
distribution of marks in the question paper may vary slightly from above table.

Reference Books:

1. Machine Learning with Python for Everyone, Mark Fenner, Pearson


2. Machine Learning, Anuradha Srinivasaraghavan, Vincy Joseph, Wiley
3. Machine Learning with Python, U Dinesh Kumar Manaranjan Pradhan, Wiley
4. Neural Networks, Fuzzy Logic, and Genetic Algorithms : Synthesis and Applications By S.
Rajshekharan, G. A. Vijayalakshmi Pai, PHI
5. KishanMehrotra, Chilukuri Mohan and Sanjay Ranka, Elements of Artificial Neural Networks,
Penram International
6. Tom Mitchell, Machine Learning, TMH
7. AthemEalpaydin, Introduction to Machine Learning, PHI
8. Andries P. Engelbrecht, Computational Intelligence - An Introduction, Wiley Publication

Course Outcomes:

After completing the course, students will be able to;

Sr. CO statement Marks %


No. weightage

CO-1 Learn the basic concepts of how to use various AI techniques. 25

CO-2 Learn, realize and implement various basic machine learning algorithms. 25

CO-3 Learn the appropriateness and steps to use fuzzy systems and Genetic algorithm 25
for engineering problem solving
CO-4 Comprehend basic concepts of Neural network and use of machine learning for 25
training

Page 2 of 3
w.e.f. AY 2018-19
GUJARAT TECHNOLOGICAL UNIVERSITY
Bachelor of Engineering
Subject Code: 3170924

List of Open Source Software/learning website:

1. https://nptel.ac.in/
2. https://www.coursera.org/
3. https://www.geeksforgeeks.org/machine-learning/
4. https://www.tutorialspoint.com/machine_learning_with_python/index.htm

Page 3 of 3
w.e.f. AY 2018-19

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy