Scribd
Upload
112 views3 pages

DLNLP - Course Outline

This document outlines a course on Deep Learning and NLP. The 3 credit course will be taught over 20 sessions by Prof. Debasmita Dey. Students will learn fundamental concepts of neural networks, CNNs, RNNs and apply them to tasks like image classification, sentiment analysis and topic modeling. Evaluation will include quizzes, assignments, projects and exams worth 100 marks total. Textbooks and references on deep learning and NLP will provide additional reading. Hands-on labs using Python and libraries like TensorFlow and NLTK will allow students to implement techniques learned.

Uploaded by

Chaitanya Jethani
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
112 views3 pages

DLNLP - Course Outline

This document outlines a course on Deep Learning and NLP. The 3 credit course will be taught over 20 sessions by Prof. Debasmita Dey. Students will learn fundamental concepts of neural networks, CNNs, RNNs and apply them to tasks like image classification, sentiment analysis and topic modeling. Evaluation will include quizzes, assignments, projects and exams worth 100 marks total. Textbooks and references on deep learning and NLP will provide additional reading. Hands-on labs using Python and libraries like TensorFlow and NLTK will allow students to implement techniques learned.

Uploaded by

Chaitanya Jethani
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

FORE School of Management, New Delhi

Course Outline
Programme: FMG-30, IMG-15, FM-04 & BDA-02

Name of the Course: Deep Learning and NLP Credit: 3.0


Term: 04 Academic Year: 2022-2023
Faculty: Prof. Debasmita Dey Office Contact No.: 4648-5527
Email: [email protected]

Introduction: With the increasing penetration of smart devices and internet there is increase and fast generation
of unstructured data like text, speech, images and video data generated over mobile, social media, and internet.
They can be used for understanding consumer behavior, fraud detection, credit risk assessment, NLP, Fintech
and marketing etc., and other hitherto unknown applications. This have necessitated the need of deep learning
capabilities. The Deep Learning thrives on the big data and is bringing new and sophisticated applications. This
course introduces the highly sophisticated areas of Deep Learning (DL) and Natural Language Processing (NLP)
in a very systematic manner using open source platform and python. The deep learning models will be developed
for solving some of the practical business problems. At the same time some of the important techniques including
deep learning to process text data will be developed for agile business processes and innovation.

Objective:
• To introduce the fundamental concepts of Neural Network based learning and their applications.
• Convolution Neural Network and Classification and Regression
• Model Architecture and Solving data augmentation
• Fundamental of NLP and of Text data Processing.
• Deep Learning models for Text data

Text Book: Deep Learning Using Python by Dr. S Lovelyn Rose, Dr. L Ashok Kumar, Dr. D Karthika Renuka
(ISBN: 9788126579914), Wiley

Reference Book:
1. Deep Learning with Python by Francois Chollet, Manning Publications
2. Machine Learning using Python by Manaranjan Pradhan and U Dinesh Kumar, Wiley
3. Natural Language Processing with Python, O’Reilly by Edward Loper, Ewan Klein and Steven Bird,
2009

Pedagogy: The course uses extensive hands-on using the programming language Python and will be delivered
through lecture, projects, presentation, and assignments. It will introduce participants to use open-source
machine learning libraries Scikit-learn, TensorFlow, Keras, NLTK to work with variety of dataset. The editing
tool used will be Jupyter (a GUI for python).

Evaluation Component and weightage: (an indicative evaluation component guideline is attached)
• Quiz : 10%
• Assignment : 10%
• Project : 15%
• Class Participation : 5%
• Mid-term Exams : 20%
• End Term Exams : 40%
________
Total 100 Marks
--------------

Page 1 of 3
Session Plan:

Session Session Theme Additional Question to


No. Reading/Cases explore/Learning
outcome*
1. Introduction to Deep Learning and Text Book : Chapter 1 ( Understand the
Neural Network, Single and Multi- Fundamentals of Neural fundamentals of deep
Layer Perceptron Networks) learning and neural
network
Hands on - Single and Multi-Layer
Perceptron
2. Convolutional Neural Network- Text Book : Chapter 2 ( Understand and
Architecture and Layers Convolutional Neural conceptualize image
ReLU, Leaky ReLU, ELU Network) segmentation using CNN.

3. Hands-On- Image Classification Lab Notes Learn to implement CNN


using CNN in Image Classification
4. Quiz + Image Augmentation and PPTs of image Understanding the concept
Transfer Learning augmentation and of Augmentation and
transfer learning will be Transfer Learning
provided during
session.
5. Hands On- Image Lab Notes Learn to implement Image
Augmentation Augmentation using Deep
Learning
6. Introduction to Recurrent Text Book : Chapter 3( Conceptualize RNN and
Neural Network, Introduction Recurrent Neural LSTM
to Long Short-Term Memory Network: Basic
Concepts)
7. Hands On- RNN and LSTM Lab Notes Learn to implement RNN
and LSTM
8. Class Assignment Assignment will be Implement the concepts of
provided in class Deep Learning in class
9. Project Presentation Group Project Implement the concepts of
Deep Learning in group
project
10. Project Presentation Group Project Implement the concepts of
Deep Learning in group
project
11. Introduction to text Tokenization, Reference Book 2: Learn various concepts of
Parts of Speech Tagging , Chapter 10.2.3 ( Text NLP
Lemmatization and Stemming Pre-Processing)
12. Hands on- Text Cleaning Process Lab Notes Perform Text Cleaning
process

13. Bag of words, Document Term Reference Book 2: Understanding Concepts


Matrix, TF-IDF Chapter 10.2.3 ( Text of TF-IDF
Pre-Processing)
14. Hands On – Word Cloud Lab Notes Perform Word Cloud from
DTM

Page 2 of 3
Session Session Theme Additional Question to
No. Reading/Cases explore/Learning
outcome*
15. Sentiment Analysis Reference Book 2: Understanding various
Chapter 10.2( aspects of Sentiment
Sentiment Analysis
Classification)
16. Hands On- Sentiment Analysis Lab Notes Perform Sentiment
Analysis on opinions
17. Topic Modeling PPTs on Topic Understand LDA and
modelling will be NMF
provided during session
18. Hands On –Topic Modelling Lab Notes Learn to implement LDA
and NMF on opinions
19. Project Presentation Group Project Implement the concepts of
NLP in group project
20. Project Presentation Group Project Implement the concepts of
NLP in group project

Note: Mid-Term and End-Term examination must be marked on a 100 max. marks basis and the
Component weight can be applied later.

For official use: -


As Benchmarked with course content in previous year, the contents of this course: (Please mark the right
option below)
(a) Is totally new
(b) Has not changed at all
(c) Has undergone less than/equal to 20% change
(d) Has undergone more than 20% change

Course Faculty – Prof. Debasmita Dey

Area Chair – Prof. Shilpi Jain

Manager (Academics-I) Dean (Academics)

Page 3 of 3

You might also like