0% found this document useful (0 votes)
22 views4 pages

Deep Learning Course Overview

The document outlines a course on Deep Learning (MCS24E3) that covers foundational concepts, optimization techniques, and various applications of deep learning. It includes prerequisites, course learning outcomes, detailed units of study, recommended textbooks, and blended learning video links. The course aims to equip students with practical skills in implementing deep learning models and understanding their applications across different domains.

Uploaded by

mailingtopriyak
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
22 views4 pages

Deep Learning Course Overview

The document outlines a course on Deep Learning (MCS24E3) that covers foundational concepts, optimization techniques, and various applications of deep learning. It includes prerequisites, course learning outcomes, detailed units of study, recommended textbooks, and blended learning video links. The course aims to equip students with practical skills in implementing deep learning models and understanding their applications across different domains.

Uploaded by

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

ELECTIVES

Course Code Course Title Category L T P Credits


MCS24E3 DEEP LEARNING Theory 58 2 - 4

Preamble
This course covers the context of deep learning, know how to use a neural network,
understand the data needs of deep learning, have a working knowledge of deep
learning, and explore the parameters for deep learning
Prerequisite
● Artificial Intelligence
● Machine Learning

Course Learning Outcomes


Upon the successful completion of the course, students will be able to
CLO CLO Statement Knowledge
Number Level
CLO1 Understand the basics of deep learning K2
CLO2 Apply the concept of optimization and generalization in deep learning.
K3
CLO3 Explore the deep learning applications. K4
CLO4 Evaluate the analysis of algorithm efficiency using different notations. K5
CLO5 Implement various deep learning models. K6

Mapping with Programme Learning Outcomes


CLOs PLO1 PLO2 PLO3 PLO4
CLO1 S M S S
CLO2 S S S M
CLO3 S S M S
CLO4 L M S S

CLO5 S M L M
S- Strong; M-Medium; L-Low

UNIT I
(11 Hrs)

Introduction to Deep Learning: Gradient-Based Learning - Architecture Design -


Optimization for Training Deep Models: Learning Differs from Pure Optimization,
Challenges in Neural Network Introduction to Neural Networks - Training a network:
loss functions, back propagation and stochastic gradient descent- Neural networks as
universal function approximate.

UNIT II
(11 Hrs)

Deep Learning Probabilistic Approach: Random Variables - Probability Distributions -


Marginal Probability - Conditional Probability - A Probabilistic Theory of Deep
Learning- Back propagation and regularization, batch normalization- What a
shallow network computes - VC Dimension and Neural Nets-Deep Vs Shallow
Networks, Convolution Networks- The Convolution Operation, Motivation, Pooling,
Convolution and Pooling as an Infinitely Strong Prior, Semi-supervised Learning.

UNIT III
(12 Hrs)

Linear (PCA, LDA) and manifolds, metric learning: Probabilistic PCA and Factor
Analysis, Independent Component Analysis (ICA), Slow Feature Analysis,
Manifold Interpretation of PCA, Auto encoders and dimensional reduction in
networks - Introduction to Convent - Architectures – Alex Net, VGG, Inception, Res
Net - Training a Convent: weights initialization, batch normalization, hyper
parameter optimization.

UNIT IV
(12 Hrs)

Optimization in deep learning: Non-convex optimization for deep networks-


Stochastic Optimization Generalization in neural networks- Spatial Transformer
Networks- Recurrent networks, LSTM - Recurrent Neural Network Language
Models- Word-Level RNNs & Deep Reinforcement Learning - Computational &
Artificial Neuroscience.

UNIT V
(12 Hrs)

Images segmentation – Object Detection – Automatic Image Captioning – Image


generation with Generative adversarial networks – Video to Text with LSTM
models – Attention models for Computer Vision. Applications of Deep Learning:
Social media filters, Drowsy driver detection, Fake currency detection, Sign
language recognition, Breast cancer detection, Emotion and gesture recognition,
Enhanced Night Vision System Case Study: Named Entity Recognition – Opinion
Mining using Recurrent Neural Networks – Parsing and Sentiment Analysis
using Recursive Neural Networks – Sentence Classification using
Convolutional Neural Networks – Dialogue Generation with LSTMs.
TEXT BOOKS
[Link] AUTHOR TITLE PUBLISHERS YEAR & EDITION
1. Ian Goodfellow, Yoshua Deep Learning MIT Press 2017 / 1st Edn
Bengio, Aaron Courville
2. Christopher M. Bishop, Deep Learning: Springer 2023 / 1st Edn
Hugh Bishop Foundations and Nature
Concepts

REFERENCE BOOKS

[Link] AUTHOR TITLE PUBLISHERS YEAR &EDITION

1. Simon J. D. Prince Understanding Deep MIT Press 2023 / 1st Edn


Book preview Learning
2. Francois Chollet Deep Learning with Manning 2018 / 2nd Edn
Python Publications
3. Phil Kim Matlab Deep Learning: Apress 2017 / 3rd Edn
With Machine Learning,
Neural Networks and
Artificial Intelligence

Pedagogy: Lectures, Group Discussions, Case studies

Course Designers:
[Link]
[Link] Priya

BLENDED LEARNING VIDEO LINKS:

UNIT I
[Link]
[Link]
[Link]
[Link]

UNIT II
[Link]
v=MZmNxvLDdV0
[Link]
v=5g1eXmQtl0E
[Link]
v=7GTAw4GYYdg
[Link]
yhKUINb7o
[Link]
v=g5y9dwXRprg

UNIT III
[Link]
v=DtEq44FTPM4
[Link]
v=GVB2ALC1T8g
[Link]
v=dXB-KQYkzNU
[Link]
v=cyIINCqyi5g
[Link]
v=ttE0F7fghfk

UNIT IV
[Link]
[Link]
[Link]
[Link]

UNIT V
[Link]
v=wp1bgd8reDk
[Link]
v=AqEF2HIMjYA
[Link]
v=IFfFwUwEOqE
[Link]
v=eMPQw7Xbjd0

You might also like