Neural Networks and Deep Learning
[As per Choice Based Credit System(CBCS)scheme]
(Effective from the academic year 2025-2026)
SEMESTER – VII
Course Code 22CS73 CIE Marks 50
Number of Lecture Hours/Week 50
03 SEE Marks
Total Number of Lecture Hours 03
40 Exam Hours
CREDITS – 03
Course Objectives:
1. Understand the fundamentals of deep learning.
2. Understanding the working of Convolution Neural Networks and RNN in decision making.
Illustrate the strength and weaknesses of many popular deep learning approaches.
Introduce major deep learning algorithms, the problem settings, and their applications to solve
real world problems
Module I Teaching
Hours
Introduction: What is a Neural Network?, The Human Brain, Models of a
Neuron, Neural Networks Viewed As Directed Graphs, Feedback, Network 8 Hours
Architectures, Rosenblatt‟s Perceptron: Introduction, Perceptron, The
Perceptron Convergence Theorem, Relation Between the Perceptron and
Bayes Classifier for a Gaussian Environment.
Module II
Multilayer Perceptrons: Introduction, Batch Learning and On-Line
Learning, The Back-Propagation Algorithm, XOR Problem, Heuristics for
Making the Back- Propagation Algorithm Perform Better, Back Propagation 8 Hours
and Differentiation
Module III
Regularization for Deep Learning: Parameter Norm Penalties - L2 8 Hours
Parameter Regularization, Dataset Augmentation, Semi-Supervised Learning.
Optimization for Training Deep Models: Challenges in Neural Network
Optimization – Ill Conditioning, Local Minima, Plateaus, Saddle Points and
Other Flat Regions.
Module IV
CONVOLUTIONAL NETWORKs: The Convolution Operation, 8 Hours
Motivation, Pooling, Convolution and Pooling as an Infinitely Strong Prior,
Variants of the Basic Convolution Function, Structured Outputs, Data Types,
Efficient Convolution Algorithms, Convolution Networks and the History of
Deep Learning.
Module V
Sequence Modeling: Recurrent and Recursive Nets: Unfolding
Computational Graphs, Recurrent Neural Networks, Bidirectional RNNs, 8 Hours
Encoder-Decoder Sequence-to- Sequence Architectures, Deep Recurrent
Networks, Recursive Neural Networks, The Long Short-Term Memory and
Other Gated RNNs
Question paper pattern:
The question paper will have ten questions.
There will be 2 questions from each module.
Each question will have questions covering all the topics under a module.
The students will have to answer 5 full questions, selecting one full question from each module.
Text Books:
1. Simon Haykin, Neural networks and Learning Machines, Third Edition, Pearson, 2016
2. Ian Goodfellow, Yoshua Bengio and Aaron Courville, Deep Learning, MIT Press,
2016.
Reference Books:
a. “Neural Network and Deep learning “ Charu c Agarwal .
b. “Deep Learning” [Link],D Narashiman,Pearson,2025
Web links and Video Lectures (e-Resources):
[Link]
[Link]
[Link]
[Link]
CO# Course Outcomes
1. Analyze and interpret the concepts of neural networks relating to artificial
intelligence
2. Illustrate the learning processes Multilayer perceptron and their statistical
properties..
3. Design deep learning models using regularization
4. Identify Various Challenges Involved In Designing And Implementing
Convolution Algorithms
5. Analyze sequential data to build recurrent and recursive models
PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO PSO2 PSO3
1
3 2 2 1 1 1 2 2 1
CO1
CO2 3 2 2 1 1 2 2
1 1 1 1 2
CO3 3 2 2 1 1 1 1 1 1 2 2 2
CO4 3 2 2 2 1 1 1 1 1 2 2 2
CO5 3 2 2 1 1 1 1 1 1 2 2 2
avg 3 1 1 1 1 1 2 2 1.8
2 2 1