Scribd
Upload
118 views3 pages

PE - IV - 102047804 - Deep Learning and Applications

Uploaded by

Rana Pratap
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
118 views3 pages

PE - IV - 102047804 - Deep Learning and Applications

Uploaded by

Rana Pratap
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

FACULTY OF ENGINEERING & TECHNOLOGY

Effective from Academic Batch: 2020-21

Programme: Bachelor of Engineering (Information Technology)

Semester: VII

Course Code: 102047804

Course Title: Deep Learning and Applications

Course Group: Professional Elective Course - IV

Course Objectives: This course aims to provide the fundamental knowledge of the theoretical
foundations, algorithms, and methodologies of Neural Network. It covers design and development of
applications using various deep learning methods such as convolutional neural networks, recurrent
neural networks, and other advancements.

Teaching & Examination Scheme:


Contact hours per week Course Examination Marks (Maximum / Passing)
Credits Theory J/V/P*
Lecture Tutorial Practical Total
Internal External Internal External
3 0 2 4 40/14 60/21 20/07 30/10 150/52
* J: Jury; V: Viva; P: Practical

Detailed Syllabus:
Sr. Contents Hours
1 Introduction to Deep Learning:
Introduction, Machine learning vs. deep learning, applications of deep learning, 5
Feature engineering, Deep learning frameworks, Bias, Variance, Regularizations
2 Review of Neural Networks:
Review of Neural network basics – architectures, activation functions, parameters, 5
Single layer and Multilayer Perceptron, Backpropagation learning
3 Convolutional Neural Networks (CNNs):
Introduction to CNNs – convolution, pooling, Deep CNNs, Different deep CNN
architectures – LeNet, AlexNet, VGG, InceptionV3, etc., Training a CNNs: weights 10
initialization, batch normalization, hyperparameter optimization, Understanding
and visualizing CNNs, Transfer learning, CNN applications
4 Recurrent Neural Networks (RNNs): 8
Introduction to RNN, Sequence modeling using RNNs,Long Short-Term Memory
(LSTM), Bidirectional LSTMs, Bidirectional RNNs, Gated Recurrent Units,
Autoencoders
5 Generative Models: 7
Restrictive Boltzmann Machines (RBMs), Belief nets, Deep belief nets, Generative
Adversarial Networks (GAN), Applications of Generative models
6 Applications: 5
Applications in computer vision, speech processing, and natural language
processing Image Classifications, Object detections, etc.
Total 40

List of Practicals / Tutorials:


1 Study of TensorFlow Framework.
2 Write the code to read a dataset using the appropriate python library and display it.
3 Implementation of multi-layer network and study network parameters for any application.
4 Implement Digit Recognition for MNIST dataset using pretrained models.
5 Implement CNN architecture for any given classification task.
6 Perform object recognition using CNN Model.
7 Implement LSTM model and test it for a given application/dataset.
8 Implement GRU model and test it for a given application/dataset
9 Implement autoencoder for any application.
10 Study of Generative models and applications.
11 Mini Project (Implementation of any application using deep learning model)

Reference Books:
1 Ian Goodfellow, Yoshua Bengio and Aaron Courville, “Deep Learning”, MIT Press, 2017.
2 Josh Patterson, Adam Gibson "Deep Learning: A Practitioner's Approach", O'Reilly Media,
2017
3 Umberto Michelucci “Applied Deep Learning. A Case-based Approach to Understanding
Deep Neural Networks” Apress, 2018.
4 Aurelion Geron, “Hands-on machine learning with Scikit-learn Keras and TensorFlow”
O’Reilley publications
5 Francois Chollet, “Deep Learning with Python” Manning.
6 Nikhil Buduma, “Fundamentals of Deep Learning: Designing Next-Generation Machine
Intelligence Algorithms”, O’Reilly publications.

Supplementary learning Material:


1 NPTEL - Swayam Courses
https://nptel.ac.in/courses/106/106/106106184/
2 Coursera courses
https://in.coursera.org/specializations/deep-learning
https://in.coursera.org/learn/introduction-to-deep-learning-boulder
https://in.coursera.org/specializations/tensorflow2-deeplearning#courses
Pedagogy:
● Direct classroom teaching
● Audio Visual presentations/demonstrations
● Assignments/Quiz
● Continuous assessment
● Interactive methods
● Seminar/Poster Presentation
● Industrial/ Field visits
● Course Projects

Suggested Specification table with Marks (Theory) (Revised Bloom’s Taxonomy):


Distribution of Theory Marks in % R: Remembering; U: Understanding; A: Applying;
R U A N E C N: Analyzing; E: Evaluating; C: Creating
15% 25% 25% 15% 20% ---

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.

Course Outcomes (CO):


Sr. Course Outcome Statements %2eightage
CO-1 Realize characteristics of deep learning models that are useful to solve
10
real-world problems.
CO-2 Understand different models to create application using deep nets. 25
CO-3 Identify and apply appropriate deep learning algorithms for analyzing
25
the data for variety of problems.
CO-4 Experiment the various challenges involved in designing deep learning
20
models.
CO-5 Apply deep learning algorithms for various applications such as 20
Computer vision, Speech processing, NLP and other.

Curriculum Revision:
Version: 1.0
Drafted on (Month-Year): June -2020
Last Reviewed on (Month-Year): -
Next Review on (Month-Year): June-2025

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