Scribd
Upload
1K views

Deep Learning Syllabus

This document outlines the syllabus for a Deep Learning course offered in the 6th semester. It includes 5 units covering topics such as neural networks, dimensionality reduction, convolutional neural networks, recurrent neural networks, and generative models. Evaluation is based on tests, assignments, and a final exam.

Uploaded by

avneets2103
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
1K views

Deep Learning Syllabus

This document outlines the syllabus for a Deep Learning course offered in the 6th semester. It includes 5 units covering topics such as neural networks, dimensionality reduction, convolutional neural networks, recurrent neural networks, and generative models. Evaluation is based on tests, assignments, and a final exam.

Uploaded by

avneets2103
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

4.3.

6 SYLLABI OF PROGRAM CORE COURSES : VI SEMESTER

Course Typ Subject L T P Cre CA MS ES CA ES Pre-requisites


No. e dits

CACSC18 CC Deep 3 1 0 4 25 25 50 - - CACSC17


Learning

COURSE OUTCOMES

1. Realize the characteristics of deep learning models that are useful to solve real-world
problems.
2. Understand various dimensionality reduction techniques.
3. Implement different deep learning algorithms
4. Recognize different methodologies to create application using deep nets.
5. Identify and apply appropriate deep learning algorithms for analysing the data for variety
of problems.
COURSE CONTENTS:

UNIT I

Introduction, History of Deep Learning, Deep Learning Success Stories, McCulloch Pitts
Neuron, Multilayer Perceptrons (MLPs), Representation Power of MLPs, Sigmoid Neurons,
Gradient Descent, Feed Forward Neural Networks, Back propagation

UNIT II

Gradient Descent (GD), Momentum Based GD, Nesterov Accelerated GD, Stochastic GD,
Principal Component Analysis(PCA): PCA and its interpretations, Singular Value
Decomposition, Auto encoders and relation to PCA, Regularization in auto encoders,
Denoising auto encoders, Sparse auto encoders

UNIT III

Regularization, Bias Variance Tradeoff, L2 regularization, Early stopping, Dataset


augmentation, Greedy Layerwise Pre-training, Better activation functions, Better weight
initialization methods, Batch Normalization

UNIT IV

90 | SCHEME OF COURSES AND EXAMINATION: B.Tech. CSE(Artificial Intelligence), NSUT MAIN CAMPUS
Convolutional Neural Networks, Learning Vectorial Representations of Words,
Convolutional Neural Networks, LeNet, AlexNet, ZF-Net, VGGNet, GoogLeNet, ResNet,
Recurrent Neural Networks, Back propagation through time (BPTT), Vanishing and
Exploding Gradients, Truncated BPTT, GRU, LSTMs

UNIT V

Encoder Decoder Models, Attention Mechanism, Attention over images, Variational


Autoencoders, Generative Adversarial Networks, Multi-task Deep Learning, Multi-view
Deep Learning, Applications: Vision, NLP, Speech
SUGGESTED READINGS

1. 1. Ian Goodfellow, YoshuaBengio 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.

Evaluation
Scheme Pre-
Course (Percentage Offering Requisites Equivalent
Type Course L T P Credits weights) Course
Code Dept. Course
Codes
Theory Practical
CA MS ES CA ES Code Name
AI
Hardware
CACSC19 CC 20 4 4 30 - 20 30 20 CSE None
and Tools
Workshop
COURSE OUTCOMES:
1. To get acquaintance with the concept of machine learning libraries, usages for different
platforms
2. Getting Exposure to R programming and hands on project in R for Analytics
3. Exposure and usage of the analytics tools such as PowerBI etc.
4. Understanding the distributed databases with Apache spark and implementation
5. Implement projects, based on the open source libraries and get acquainted with the
current trends in the industry.

COURSE CONTENTS:

UNIT-1
Introduction to Machine Learning on AI Hardware

91 | SCHEME OF COURSES AND EXAMINATION: B.Tech. CSE(Artificial Intelligence), NSUT MAIN CAMPUS

You might also like