DR. A.P.J.

ABDUL KALAM TECHNICAL UNIVERSITY LUCKNOW

Evaluation Scheme & Syllabus

For

B.Tech. Minor Degree

in

Artificial Intelligence & Machine Learning

Eligible Branches-
All Branches EXCEPT Computer Science and Engineering
Engineering,, Electronics and
Communication Engineering and allied Branches

As per NEP 2020

(Effective from the Session: 2023-24)

2023
 STUDY & EVALUATION SCHEME
Minor Degree in Artificial Intelligence and Machine Learning

Eligible Branches-
All Branches EXCEPT Computer Science and Engineering, Electronics and Communication
Engineering and allied Branches

COURSE CURRICULUM

Practical End
Examination

Examination
Theory End
Sessional

Semester

Semester
Practical
Theory Sessional
Semester

Periods

Credits
Sl. No.

Total
Subject (TS)
Subject
Codes

L T P CT TA CT+TA PS TE PE

Introduction
to AI &
1 IV MNAM401 3 1 0 30 20 50 -- 100 -- 150 4
Machine
Learning

Introduction
2 V MNAM501 to Data 3 1 0 30 20 50 -- 100 -- 150 4
Analytics

Deep
Learning
3 VI MNAM601 3 1 0 30 20 50 -- 100 -- 150 4
and Neural
Network

Special
topics in
4 VII MNAM701 3 1 0 30 20 50 -- 100 -- 150 4
Artificial
Intelligence

5 VIII MNAM801 AI Lab 0 0 4 -- -- -- 50 -- 50 100 2

Total 700 18
 Syllabus
MNAM401 Introduction to AI & Machine Learning
Course Outcome ( CO)
At the end of course , the student will be able to understand
CO 1 Provide you with the knowledge and expertise to become a proficient data scientist.
Demonstrate an understanding of statistics and machine learning concepts that are vital for
CO 2
data science
The student will learn to apply knowledge representation techniques and problem solving strategies to
CO 3
common AI applications. Produce Python code to statistically analyse a dataset;
Critically evaluate data visualisations based on their design and use for communicating stories
CO 4
from data;
DETAILED SYLLABUS
Proposed
Unit Topic
Lecture
Defining Artificial Intelligence, Defining AI techniques, Using Predicate Logic and
Representing Knowledge as Rules, Representing simple facts in logic, Computable
I 12
functions and predicates, Procedural vs Declarative knowledge, Logic Programming,
Mathematical foundations: Matrix Theory and Statistics for Machine Learning.

Idea of Machines learning from data, Classification of problem –Regression and

II 08
Classification, Supervised and Unsupervised learning.

Linear Regression: Model representation for single variable, Single variable Cost
III 10
Function, Gradient Decent for Linear Regression, Gradient Decent in practice.

Logistic Regression: Classification, Hypothesis Representation, Decision Boundary,

IV Cost function, Advanced Optimization, Multi-classification (One vs All), Problem of 07
Over fitting.

Discussion on clustering algorithms and use-cases cantered around clustering and

V 05
classification.

Text books:
1. Saroj Kaushik, Artificial Intelligence, Cengage Learning, 1st Edition 2011.
2. Anindita Das Bhattacharjee, “Practical Workbook Artificial Intelligence and Soft Computing for
beginners, Shroff Publisher-X team Publisher.
3. Yuxi (Hayden) Liu, “Python Machine Learning by Example”, Packet Publishing Limited, 2017.
4. Tom Mitchell, Machine Learning, McGraw Hill, 2017.
5. Christopher M. Bishop, Pattern Recognition and Machine Learning, Springer, 2011.
6. T. Hastie, R. Tibshirani, J. Friedman. The Elements of Statistical Learning, 2e, 2011.

Corresponding Online Resources:

1. Artificial Intelligence,https://swayam.gov.in/nd2_cec20_cs10/preview.
MNAM501 Introduction to Data Analytics
Course Outcome ( CO)
At the end of course , the student will be able to understand
Provide you with the knowledge and expertise to become a proficient data scientist
CO 1

Demonstrate an understanding of statistics and machine learning concepts that are vital for
CO 2
data science;
CO 3 Produce Python code to statistically analyze a dataset;
Critically evaluate data visualizations based on their design and use for communicating stories
CO 4
from data;
DETAILED SYLLABUS
Proposed
Unit Topic
Lecture
Introduction to Data Science, Different Sectors using Data science, Purpose and
I 07
Components of Python in Data Science.

Data Analytics Process, Knowledge Check, Exploratory Data Analysis (EDA), EDA-
II Quantitative technique, EDA- Graphical Technique, Data Analytics Conclusion and 07
Predictions.

Feature Generation and Feature Selection (Extracting Meaning from Data)-

III
Motivating application: user (customer) retention- Feature Generation 11
(brainstorming, role of domain expertise, and place for imagination)- Feature
Selection algorithms.

Data Visualization- Basic principles, ideas and tools for data visualization, Examples
IV of inspiring (industry) projects- Exercise: create your own visualization of a complex 10
dataset.

Applications of Data Science, Data Science and Ethical Issues- Discussions on

V privacy, security, ethics- A look back at Data Science- Next-generation data 5
scientists.
Text books:
1. Joel Grus, Data Science from Scratch, Shroff Publisher Publisher /O’Reilly Publisher Media
2. Annalyn Ng, Kenneth Soo, Numsense! Data Science for the Layman, Shroff Publisher Publisher
3. Cathy O’Neil and Rachel Schutt. Doing Data Science, Straight Talk from The Frontline. O’Reilly
Publisher Media.
4. Jure Leskovek, Anand Rajaraman and Jeffrey Ullman. Mining of Massive Datasets. v2.1,
Cambridge University Press.
5. Jake VanderPlas, Python Data Science Handbook, Shroff Publisher Publisher /O’Reilly Publisher
Media
6. Philipp Janert, Data Analysis with Open Source Tools, Shroff Publisher Publisher /O’Reilly
Publisher Media.
MNAM601 Deep Learning and Neural Network
Course Outcome ( CO)
At the end of course , the student will be able to understand
To strengthen important Mathematical concepts required for Deep learning and neural
CO 1
network.
CO 2 To get a detailed insight of advanced algorithms of ML.
CO 3 Produce Python code or simulate training algorithms ;
CO 4 Critically evaluate and Creating and deploying networks ;
DETAILED SYLLABUS
Proposed
Unit Topic
Lecture
I Information flow in a neural network, understanding basic structure and ANN. 08

II Training a Neural network, how to determine hidden layers, recurrent neural 08

network.

III Convolutional neural networks, image classification and CNN. 10

IV RNN and LSTMs. Applications of RNN in real world. 09

V Creating and deploying networks using tensor flow and keras. 7

Text books:
1. John Paul Mueller, Luca Massaron, Deep Learning for Dummies, John Wiley & Sons.
2. Adam Gibson, Josh Patterson, Deep Learning, A Practitioner’s Approach, Shroff Publisher /O’Reilly
Publisher Media.
3. Christopher M. Bishop, Neural Networks for Pattern Recognition, Oxford.

Corresponding Online Resources:

1. Fuzzy Logic and Neural Networks,

https://swayam.gov.in/nd1_noc20_ge09/preview.
MNAM701 Special topics in Artificial Intelligence
Course Outcome ( CO)
At the end of course , the student will be able to understand
To give fundamental knowledge to the students so that they can understand what the AI is and
CO 1 study important topics related to the field.

CO 2 To understand various AI techniques.

CO 3 To decide when to use which type of AI technique

CO 4 To understand the role of uncertainty measures and principles in AI.

DETAILED SYLLABUS
Proposed
Unit Topic
Lecture
Bayesian Filtering; Recurrent Neural Networks, Deep Neural Networks, Deep
I 09
Reinforcement Learning.

Self-Play Networks, Generative Adversarial Networks, Learning from Concept-

II 07
Drifting Data Streams.

Audio Signal Processing Basics, mirtoolbox contains many useful audio processing
III library functions, VOICEBOX: Speech Processing Toolbox for MATLAB, Audio 09
processingin Matlab.

Architectures for second generation knowledge based systems, Distributed AI and

IV 10
its applications.

An introduction to neurocomputing and its possible role in AI, The role of

V 7
uncertainty measures and principles in AI.

Text books:
1. Dr. Nilakshi Jain, Artificial Intelligence: Making a System Intelligent, John Wiley & Sons.
2. Artificial Intelligence & Soft Computing for Beginners, 3rd Edition-2018, by Anindita Das, Shroff
Publisher Publisher.
3. Artificial Intelligence: A Modern Approach, 3rd Edition, by Stuart Russell and Peter Norvig, Pearson
Publisher.
4. New Artificial Intelligence (Advanced), Takashi Maeda and Fumio Aoki, Ohmsha Publisher.
 MNAM801 AI Lab
1. Implementation of logical rules in Python.

2. Using any data apply the concept of:

a. Liner regression

b. Gradient decent

c. Logistic regression
3. To add the missing value in any data set.

4. Perform and plot under fitting and over fitting in a data set.

5. Implementation of clustering and classification algorithms.

6. Python Environment setup and Essentials.

7. Mathematical computing with Python (NumPy).

8. Scientific Computing with Python (SciPy).

9. Data Manipulation with Pandas.

10. Prediction using Scikit-Learn

11. Data Visualization in python using matplotlib

12. Introduction to Kaggle and how it can be used to enhance visibility.

13. Build general features to build a model for text analytics.

14. Build and deploy your own deep neural network on a website using tensor flow.

Note: Subject Teacher May add/ delete the experiments as per the subject requirements.