Scribd
Upload
41 views2 pages

Syllabus

fds syllabus

Uploaded by

Muddamsetty Arunkalyan
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
Download as pdf or txt
41 views2 pages

Syllabus

fds syllabus

Uploaded by

Muddamsetty Arunkalyan
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
Download as pdf or txt
Download as pdf or txt
You are on page 1/ 2

AY 2022-23 J. B. Institute of Engineering and Technology B.

Tech: CSE(AI & ML)

onwards (UGC Autonomous) III Year – I Sem

Course
DEEP LEARNING
Code: L T P D
(Common to AI&ML, AI&DS, CSE(AI&ML))
L31AB

Credits: 3 3 0 0 0

Pre-Requisites:
1. Probability Statistics, linear algebra. Machine learning .
Course Objectives:
The Student will:
1. Get introduced to various learning techniques of machine learning and understand
differences between machine learning and deep learning
2. Understand and analyse optimization techniques and improvements in learning methods
3. Appreciate, understand and apply neural networks as tools for complete learning problems
4. Investigate and deploy/club multi-layer neural networks for learning related to images, text
and speech sequences.
5. Appreciate, understand and implement Deep learning in real world practical problems
Module 1:
Introduction to Deep Learning
Introduction to Deep Learning, Brief History of Deep Learning, AI, Machine Learning and Deep
Learning, Statistical Learning,
Bayesian Learning, Decision Surfaces, Success stories of Deep Learning
Module 2:
Linear Classifiers
Linear Classifiers, Linear Machines with Hinge Loss, Optimization Techniques, Gradient Descent,
Batch Optimization,
Revisiting Gradient Descent, Momentum Optimizer, RMS Prop, Adam.
Module 3:
Neural Network
Introduction to Neural Network, Multilayer Perceptron, Back Propagation Learning, Unsupervised
Learning with Deep Network, Auto encoders, Convolutional Neural Network, Building blocks of
CNN, Transfer Learning, LSTM Networks, NN in python

67
Module 4:
Deep Neural Net
Effective training in Deep Net- early stopping, Dropout, Batch Normalization, Instance
Normalization, Group Normalization,
Recent Trends in Deep Learning Architectures, Residual Network, Skip Connection Network, Fully
Connected CNN, CNN in Python
Module 5:
Applications of Deep Learning
Classical Supervised Tasks with Deep Learning, Image Denoising, Semantic Segmentation, Object
Detection, Generative Modeling with Deep Learning,
Variational Auto encoder, Generative Adversarial Network, Object recognition with Python.
Text Books:
1. Deep Learning- Ian Goodfelllow, YoshuaBenjio, Aaron Courville, The MIT Press
2. Pattern Classification- Richard O. Duda, Peter E. Hart, David G. Stork, John Wiley & Sons Inc.

Reference Books:
1. Deep Learning: A Practitioner's Approach by Josh Patterson & Adam Gibson, OReilly Press
2. Python Deep Learning: Exploring deep learning techniques and neural network architectures
with PyTorch, Keras, and TensorFlow, 2nd Edition by Ivan Vasilev, Pakt Publication.

E - Resources:
1. https://nptel.ac.in/courses/106/105/106105215/
2. https://www.slideshare.net/LuMa921/deep-learning-a-visual-introduction
3. https://yiqiaoyin.files.wordpress.com/2018/02/deep-learning-notes.pdf

Course Outcomes:
The student will be able to:
1. Identify tools of machine learning and deep learning, appropriate to any problems
2. Apply optimization techniques to improve the quality of various learning solutions.
3. Apply and investigate, neural network for complete learning problems.
4. Deploy deep learning methods in the area of multidimensional and sequential inputs.
5. Investigate the scope of implementation of various deep learning techniques in any real world
problem.

68

You might also like