Scribd
Upload
72 views1 page

DEEP LEARNING-Syllabus

this is document to describe the deep learning

Uploaded by

Mastanaihnaidu Yasam
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
72 views1 page

DEEP LEARNING-Syllabus

this is document to describe the deep learning

Uploaded by

Mastanaihnaidu Yasam
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/ 1

B V Raju Institute of Technology/ B.Tech. CSE w.e.f.

2020-2021

DEEP LEARNING
(DOMAIN: COGNITIVE SCIENCE AND ARTIFICIAL INTELLIGENCE)
PROFESSIONAL ELECTIVE - VI
Year/ Course Hours /
Regulation Category Credits Maximum Marks
Sem Code Week
L T P C CIE SEE Total
R20 IV / I PE
3 - - 3 40 60 100

Pre-requisites: Probability and Statistics, Machine Learning

Objectives: The students will learn the following:


1. Understand the Deep and wide Neural Networks
2. Understand the Convolutional Neural Networks (CNN) its types
3. Understand the Recurrent Neural Networks (RNN) its various types
4. Understand the Generative Adversarial Networks (GAN)
5. Understand the Unsupervised Deep Learning and RBMs.

Unit I: (10 Periods)


Deep and wide Neural Networks
Wide neural networks: Deep learning revisited wide layers. Dense Deep Neural Networks, Sparse deep
neural networks. Hyper parameter optimization.

Unit II: (10 Periods)


Convolutional Neural Networks (CNN)
Introduction to CNN, Convolution in n-dimensions: 1-D,2-D, n-D. Convolutional layers: Conv2D, the layer+
activation combo. Pooling Strategies.

Unit III: (10 Periods)


Recurrent Neural Networks (RNN)
Introduction to RNN: Simple RNNs, Embedding Layers. Long Short-term memory (LSTM) models. Sequence-
to-vector models: Unsupervised model, Vector-to-sequence models: Bi-directional LSTM. Sequence-to-
sequence models.

Unit IV: (8 Periods)


Generative Adversarial Networks (GAN)
Introducing adversarial learning, Training GAN: An MLP model, A convolutional model. Comparing GANs
and VAEs.

Unit V: (12 Periods)


Unsupervised Deep Learning
Introduction to unsupervised learning. Encoding and decoding layers: Encoding layers, Decoding layers,
loss function, learning and testing. Deep Auto encoders: making deep auto-encoders, batch normalization,
Dropout.
Restricted Boltzmann Machines (RBM): Introduction to RBMs, BMs, RBMs, Bernoulli RBMs.

Outcomes: Upon the successful completion of the course, the student will be able:
1. To infer knowledge about the Deep and wide Neural Networks
2. To apply the Convolutional Neural Networks (CNN)on real world problems
3. To apply the Recurrent Neural Networks (RNN) its various types on some real-world problems
4. To apply the Generative Adversarial Networks (GAN) on real time data.
5. To understand the concept of Unsupervised Deep Learning and apply RBMs on real time data.

Textbooks:

1. PabloRivas. Deep Learning for Beginners: A beginner's guide to getting up and running with deep
learning from scratch using Python. Packt Publishing Ltd, 2020.
References:
1. Goodfellow Ian, et al. Deep learning. Vol. 1. No. 2. Cambridge: MIT press, 2016.
2. Seth Weidman, Deep learning from Scratch Building with Python from First Principles, O’Reilly: First
Edition, 2019.

You might also like