Scribd
Upload
13 views

Guidelines_Deep Learning

The document outlines the guidelines for the B.Sc. (H) Computer Science VI Semester and B.A. Programme VI Semester course on Deep Learning, effective from the academic year 2024-25. It includes topics such as neural networks, deep neural networks, convolutional neural networks, recurrent neural networks, unsupervised deep learning, and applications in various fields. Additionally, it provides essential readings, additional references, and a suggested practical list for hands-on experience using Python.

Uploaded by

Dinesh Yadav
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
13 views

Guidelines_Deep Learning

The document outlines the guidelines for the B.Sc. (H) Computer Science VI Semester and B.A. Programme VI Semester course on Deep Learning, effective from the academic year 2024-25. It includes topics such as neural networks, deep neural networks, convolutional neural networks, recurrent neural networks, unsupervised deep learning, and applications in various fields. Additionally, it provides essential readings, additional references, and a suggested practical list for hands-on experience using Python.

Uploaded by

Dinesh Yadav
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/ 2

Guidelines of B.Sc. (H) Computer Science VI Semester/ B.A.

Programme VI Semester
DSC-A6/DSE: DEEP LEARNING
(NEP UGCF 2022)
(Effective from Academic Year 2024-25)

S.No Topic Chapter Reference No. of hours


1 Unit 1 Introduction to neural networks:

Artificial neurons, perceptron, 1 [2] (8 Hours)


computational models of neurons, Structure
of neural networks,
Multilayer feedforward neural networks 6 (6.1, 6.2, 6.3, 6.4, [1]
(MLFFNN),Backpropagation learning, 6.5.1, 6.5.2, 6.5.4 )
Empirical risk minimization, bias-variance
tradeoff, Regularization, output units: linear,
softmax , hidden units:tanh, RELU
2 Unit 2 Deep neural networks:

Difficulty of training DNNs, Greedy 7 (7.1) [1] (8 Hours)


layerwise training, Optimization for training 8 (8.2, 8.3.1, 8.3.2,
DNN’s, Newer optimization methods for 8.5.1, 8.5.2, 8.5.3,
neural networks (AdaGrad, RMSProp, 8.7.1)
Adam), Regularization methods (dropout,
drop connect, batch normalization).
3 Unit 3 Convolution neural
networks(CNNs):

Introduction to CNN - convolution, 9 (9.1, 9.2, 9.3, 9.4) [1] (8 Hours)


pooling, Deep CNNs - LeNet, AlexNet.
Training CNNs, weights initialization,
batch normalization, hyperparameter
optimization, Using a pre trained convnet
4 Unit 4 Recurrent neural networks
(RNNs):

Sequence modeling using RNNs, 10 (10.1, 10.2 upto pg [1] (8 Hours)


Backpropagation through time, LongShort 372,
Term Memory (LSTM), Bidirectional RNN 10.3, 10.7, 10.10.1)
5 Unit 5 Unsupervised deep learning:

Autoencoders, 14 (14.1, 14.2) [1] (8 Hours)


Generative Adversarial Networks. 20 (20.20.4) [1]
6 Unit 6 Applications:

Computer vision, Speech recognition and 12 (12.2, 12.3, 12.4.1- [1] (5 Hours)
NLP. 12.4.4)

Essential/recommended readings

1. Ian Goodfellow, Yodhua Bengio and Aaron Courville, Deep Learning, MIT Press Book, 2016.
2. Bunduma, N., Fundamentals of Deep Learning, 1st edition, O’reilly Books, 2017.
3. Francois Chollet, Deep Learning with python, 2nd edition, Meaning Publications Co, 2021.(Can be
used for Practicals)
Additional References

1. 12. Heaton, J., Deep Learning and Neural Networks, 1st edition, Heaton Research Inc., 2015.

Suggested Practical List:

The following practical are to be conducted using Python.

1. Implement a deep-neural feed-forward network for estimating the price of house, given real-estate data
(Boston Housing Price)
2. Implement a feed-forward neural networks for classifying movie reviews as positive or negative (using
IMDB dataset)
3. Implement a deep-neural network for classifying news wires by topic (Reuters dataset).
4. Implement CNN for classifying MNIST dataset
5. Classify MNIST dataset using any pertained model
6. Create a model for time-series forecasting using RNN/LSTM
7. Implement an auto-encoder

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