Vidyavardhaka College of Engineering

Gokulam III stage, Mysuru – 570 002

Autonomous Institute under Visvesvaraya Technological University (VTU)
Accredited by NBA (2020- 2023) & NAAC with ‘A’ Grade (2018 - 2023)

SEMESTER – III
Course Name : Deep Learning Course Code: MDLCS204

No. of Lecture Hours / Week : 03 CIE Marks: 50

No. of Tutorial / Practical
: 02 SEE Marks: 50
Hours / Week
Total No. of Lecture +
: 40 + 10 = 50 SEE Duration: 03 hrs.
Tutorial / Practical Hours
L:T:P : [Link] Credits: 04
COURSE OVERVIEW:
Deep learning is part of a broader family of machine learning methods based on artificial neural
networks. Deep learning architectures such as deep neural networks, recurrent neural networks and
convolutional neural networks have been applied to fields including computer vision, speech
recognition, natural language processing, audio recognition, social network filtering, machine
translation, bioinformatics, drug design, medical image analysis, material inspection and board game
programs, where they have produced results comparable to and in some cases superior to human
experts. This course focuses on developing basic deep learning models for solving real world
applications.
COURSE LEARNING OBJECTIVES (CLO):
● To introduce basics of neural network and deep learning concepts
● To familiarize with deep learning techniques
● To study use cases of deep learning models
TEACHING
MODULES
HOURS
MODULE 1: Introduction to Deep Learning
Introduction, Shallow Learning, Deep Learning, Why to use Deep Learning, How Deep
Learning Works, Deep Learning Challenges, How Learning Differs from Pure Optimization, 08
Challenges in Neural Network Optimization
Textbook 1: Ch 1.1 – 1.6, Textbook 2: 8.1,8.2
MODULE 2: Training Supervised Deep Learning Networks
Introduction, Convolution Neural Network, Architecture of CNN, Training Convolution
Neural Networks, Loss Functions and Softmax Classifier, Gradient Descent-Based 08
Optimization Techniques, Challenges in Training Deep Networks
Textbook 1: Ch 2.1-2.2,2.5,3.1-3.5
MODULE 3: Deep Learning Networks
Deep convolutional neural network (DCNN), LeNet, Recognizing CIFAR-10 images with
deep learning, Generative Adversarial Networks, Some GAN applications, Word
Embeddings: Distributed representations, Word2Vec, Exploring GloVe, Using pre-trained
08
embeddings
Textbook3: Ch 3, 4, 5
 Vidyavardhaka College of Engineering
Gokulam III stage, Mysuru – 570 002
Autonomous Institute under Visvesvaraya Technological University (VTU)
Accredited by NBA (2020- 2023) & NAAC with ‘A’ Grade (2018 - 2023)
MODULE 4: Recurrent Neural Network
Recurrent Neural Network, Long Short-Term Memory, Gated Recurrent Unit, back
propagation through time, Bidirectional RNNs, Stateful RNN, Case study-predicting 08
electricity consumption, RNN variants
Textbook3: Ch 6
MODULE 5: Additional Deep Learning Models
Regression Network, Autoencoders for unsupervised learning, Composing deep networks,
08
Generative models
Textbook3: Ch 7
PART A
The following programs can be implemented using Python libraries such as Keras,
TensorFlow, NumPy, etc. Suitable datasets can be downloaded from Keras, Kaggle,
etc. for model training and validation.

1. Write a program to demonstrate the working of a deep neural network for classification
task.
2. Build and demonstrate an autoencoder network using neural layers for data compression
on image dataset.
3. Desing and implement a convolutional neural network(Convnet) for classification of
image dataset.
4. Design and implement a neural based network for generating word embedding for words
in a document corpus.
5. Desing and implement a deep learning network for classification of textual documents.
6. Design and implement a Generative Adversarial Network(GAN) for synthesizing images
from random noise inputs.
7. Write a program to enable pre-train models to classify a given image dataset.
10

PART – B

Open Ended Enquiry Problems

Students must apply suitable technique based on the dataset for applications such as
1. Image Recognition and Computer Vision
2. Natural Language Processing (NLP)
3. Generative Models

TYPE OF LAB EXERCISE LAB EXERCISE PROBLEM

PROBLEMS NUMBERS
DEMONSTRATION 1, 2
EXERCISE 3, 4, 5
STRUCTURED ENQUIRY 4, 5, 6, 7
OPEN ENDED PART-B

Skill Development Activities

Students are required to acquaint with the Deep Learning techniques through design and
implementation of various models. At the end, the students need to present their mini project on Deep
 Vidyavardhaka College of Engineering
Gokulam III stage, Mysuru – 570 002
Autonomous Institute under Visvesvaraya Technological University (VTU)
Accredited by NBA (2020- 2023) & NAAC with ‘A’ Grade (2018 - 2023)
Learning technique as a part of ABA evaluation.
Text Books:
1. M. Arif Wani Farooq Ahmad Bhat Saduf Afzal Asif Iqbal Khan, Advances in Deep Learning,
Springer, 2020
2. Ian Goodfellow, Yoshua Bengio, Aaron Courville, Deep Learning, MIT Press, 2016.
3. Antonio Gulli, Sujit pal, Deep Learning with Keras, PACT publication, 2017.
Reference Books:
1. Charu C. Aggarwal, Neural Networks and Deep Learning, Springer, 2018.
2. Aurelien Geron, Hands on Machine Learning with Scikit Learn and Tensor Flow, Second Edition,
O’reilly Publication, 2019
COURSE OUTCOMES (COs)
At the end of the course, students will be able to
CO1 Explain the concepts of neural networks and deep learning techniques
CO2 Illustrate the application of deep learning models to solve real world problems
CO3 Design deep learning models with suitable configuration for predictive analytics
CO4* Implement deep learning models to solve real world problems
*CO4 shall be assessed in ABA

PO1 PO2 PO3

CO1 2
CO2 2
CO3 2
CO4 2
Avg. 2 2 2