Scribd
Upload
33 views3 pages

Bcse332l Deep-Learning TH 1.0 0 Bcse332l

The document provides details about a Deep Learning course including its objectives, outcomes, modules, textbooks and evaluation methods. The course covers neural network fundamentals, convolutional networks, improving deep networks, recurrent networks, recursive networks, advanced networks and deep reinforcement learning.

Uploaded by

Haresh
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
33 views3 pages

Bcse332l Deep-Learning TH 1.0 0 Bcse332l

The document provides details about a Deep Learning course including its objectives, outcomes, modules, textbooks and evaluation methods. The course covers neural network fundamentals, convolutional networks, improving deep networks, recurrent networks, recursive networks, advanced networks and deep reinforcement learning.

Uploaded by

Haresh
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/ 3

Item 66/29 - Annexure - 25

Short Syllabus

BCSE332L Deep Learning (3-0-0-3)

Neural Networks Basics - Deep Neural Networks – Forward and Back Propagation; Deep
Convolutional Models – ResNet, AlexNet, InceptionNet ; Mini-batch Gradient Descent –
Exponential Weighted Averages - Hyperparameter tuning – Batch Normalization ; Recurrent
Neural Networks - Bidirectional RNN - BERT ; Recursive Neural Networks - Echo State
Networks - Long Short-Term Memory; Transfer Learning – Generative Adversarial Network–
Region based CNN – Fast RCNN - You Only Look Once – Single shot detector ; Deep
Reinforcement Learning - Deep Q-Learning - Model based Reinforcement Learning.

Proceedings of the 66th Academic Council (16.06.2022) 645


Item 66/29 - Annexure - 25

Course code Course Title L T P C


BCSE332L Deep Learning 3 0 0 3
Pre-requisite NIL Syllabus version
1.0
Course Objectives
1. Introduce major deep neural network frameworks and issues in basic neural
networks
2. To solve real world applications using Deep learning

Course Outcomes
At the end of this course, student will be able to:
1. Understand the methods and terminologies involved in deep neural network,
differentiate the learning methods used in Deep-nets.
2. Identify and apply suitable deep learning approaches for given application.
3. Design and develop custom Deep-nets for human intuitive applications
4. Design of test procedures to assess the efficiency of the developed model.
5. To understand the need for Reinforcement learning in real – time problems.

Module:1 Introduction to neural networks and deep neural networks 7 hours


Neural Networks Basics - Functions in Neural networks – Activation function, Loss function -
Function approximation - Classification and Clustering problems - Deep networks basics -
Shallow neural networks – Activation Functions – Gradient Descent – Back Propagation –
Deep Neural Networks – Forward and Back Propagation – Parameters - Hyperparameters
Module:2 Convolution neural networks 6 hours
Foundations of Convolutional Neural Networks – CNN operations – Architecture – Simple
Convolution Network – Deep Convolutional Models – ResNet, AlexNet, InceptionNet and
others
Module:3 Improving deep neural networks 8 hours
Mini-batch Gradient Descent – Exponential Weighted Averages – Gradient Descent with
Momentum – RMSProp and Adam Optimization – Hyperparameter tuning – Batch
Normalization – Softmax Regression – Softmax classifier – Deep Learning Frameworks –
Data Augmentation - Under-fitting Vs Over-fitting
Module:4 Recurrent networks 6 hours
Recurrent Neural Networks - Bidirectional RNNs, Encoder, Decoder, Sequence-to-Sequence
Architectures, Deep Recurrent Networks, Auto encoders - Bidirectional Encoder
Representations from Transformers (BERT)
Module:5 Recursive neural networks 6 hours
Long-Term Dependencies - Echo State Networks - Long Short-Term Memory and Other
Gated RNNs - Optimization for Long-Term Dependencies - Explicit Memory
Module:6 Advanced Neural networks 6 hours
Transfer Learning – Transfer Learning Models – Generative Adversarial Network and their
variants – Region based CNN – Fast RCNN - You Only Look Once – Single shot detector
Module:7 Deep reinforcement learning 5 hours
Deep Reinforcement Learning – Q-Learning – Deep Q-Learning – Policy Gradients -
Advantage Actor Critic (A2C) and Asynchronous Advantage Actor Critic (A3C) – Model
based Reinforcement Learning - Challenges
Module:8 Contemporary issues 1 hours

Total Lecture hours: 45 Hours

Proceedings of the 66th Academic Council (16.06.2022) 651


Item 66/29 - Annexure - 25

Text Book(s)
1. Deep Learning, Ian Goodfellow Yoshua Bengio Aaron Courville, MIT Press, 2017
2 Neural Networks and Deep Learning, Michael Nielsen,, Determination Press
Reference Books
1. Deep Learning Step by Step with Python, N D Lewis, 2016
2. Deep Learning: A Practitioner's Approach, Josh Patterson, Adam Gibson, O'Reilly
Media, 2017
3 Applied Deep Learning. A Case-based Approach to Understanding Deep Neural
Networks, Umberto Michelucci, Apress, 2018.
4 Deep Learning with TensorFlow: Explore neural networks with Python, Giancarlo
Zaccone, Md. RezaulKarim, Ahmed Menshawy, Packt Publisher, 2017.
Mode of Evaluation: CAT / Written Assignment / Quiz / FAT
Recommended by Board of Studies 09-05-2022
Approved by Academic Council No. 66 Date 16-06-2022

Proceedings of the 66th Academic Council (16.06.2022) 652

You might also like