0% found this document useful (0 votes)
53 views8 pages

DNN Ho

The document provides details about a course on deep neural networks including: 1) The course aims to introduce students to basic concepts and techniques of deep learning including neural networks, optimization methods, regularization, convolutional networks, recurrent networks, attention models and applications to time series modeling. 2) The course content is structured over 15 sessions covering topics such as feedforward networks, optimization algorithms, convolutional networks, recurrent networks, attention mechanisms and neural architecture search. 3) References include textbooks on deep learning and papers on neural architecture search and time series forecasting with deep learning methods.

Uploaded by

rahulsgayke
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
0% found this document useful (0 votes)
53 views8 pages

DNN Ho

The document provides details about a course on deep neural networks including: 1) The course aims to introduce students to basic concepts and techniques of deep learning including neural networks, optimization methods, regularization, convolutional networks, recurrent networks, attention models and applications to time series modeling. 2) The course content is structured over 15 sessions covering topics such as feedforward networks, optimization algorithms, convolutional networks, recurrent networks, attention mechanisms and neural architecture search. 3) References include textbooks on deep learning and papers on neural architecture search and time series forecasting with deep learning methods.

Uploaded by

rahulsgayke
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/ 8

BIRLA INSTITUTE OF TECHNOLOGY & SCIENCE, PILANI

WORK INTEGRATED LEARNING PROGRAMMES


Digital
Part A: Content Design
Course Title Deep Neural Network

Course No(s)

Credit Units 4

Content Authors Ms. Seetha Parameswaran

Version 1.0

Date September 24th 2022

Course description
AIML* ZG511 Deep Neural Networks
Introduction to neural networks, approximation properties, back propagation, deep
network training, regularization and optimization, convolution neural networks,
recurrent neural networks, attention models, transformers, neural architecture search,
federated learning, meta learning, applications in time series modelling and forecasting,
online (incremental) learning.

Pre-requisistes:
AIML* ZC416 Mathematical Foundations for Machine Learning
AIML* ZC418 Introduction to Statistical Methods
AIML* ZG565 Machine Learning

Course Objectives
No Course Objective

CO1 Introduce students to the basic concepts and techniques of Deep Learning.

CO2 Students will be able apply deep learning models to applications.

CO3 Students will be able to evaluate deep learning algorithms.


Text Book(s)
T1 Dive into Deep Learning by Aston Zhang, Zack C. Lipton, Mu Li, Alex J. Smola.
https://d2l.ai/chapter_introduction/index.html

Reference Book(s) & other resources


R1 Deep Learning by Ian Goodfellow, Yoshua Bengio, Aaron Courville. MIT Press 2016.

R2 Introduction to Deep Learning by Eugene Charniak. The MIT Press 2019

R3 Deep Learning with Python by Francois Chollet. 1st Edition. Manning Publications
https://livebook.manning.com/book/deep-learning-with-python/part-1/

R4 Deep Learning for Time Series Forecasting by Jason Brownlee

R5 Neural Architecture Search: A Survey by Thomas Elsken, Jan Hendrik Metzen, Frank
Hutter https://arxiv.org/pdf/1808.05377.pdf

Content Structure

1 Fundamentals of Neural Network ( 4 hrs)


1.1 Objective of the course
1.2 Supervised, unsupervised, semi-supervised and reinforcement learning
problems.
1.3 Why Deep Learning?
1.4 Applications of Deep Learning
1.5 Perceptron and Perceptron learning algorithm
1.6 Multilayer Perceptron (MLP)
1.7 MLP as classifiers and Universal approximators
1.8 Issue of Depth and Width

2 Deep Feedforward Neural Networks ( 4 hrs)


2.1 Forward and backward propagation
2.2 Computation graph
2.3 Gradient Descent algorithm
2.4 Impact of depth in DNN

3 Optimization of Deep models ( 2 hrs)


3.1 Challenges in Neural Network Optimization – saddle points and plateau
3.2 Non-convex optimization intuition
3.3 Overview of optimization algorithms
3.4 Mometum based algorithms
3.5 Algorithms with Adaptive Learning Rates

4 Regularization for Deep models ( 2 hrs)


4.1 Model Selection
4.2 Underfitting, and Overfitting
4.3 L1 and L2 Regularization
4.4 Dropout
4.5 Challenges - Vanishing and Exploding Gradients, Covariance shift
4.6 Parameter Initialization
4.7 Batch Normalization

5 Convolutional Networks ( 4 hrs)


5.1 Convolutions for Images
5.2 Learning a Kernel
5.3 Padding and stride, Channels, Pooling
5.4 Design of CNN
5.5 Popular CNN architectures
5.6 Transfer Learning
5.7 Applications of CNN

6 Sequence Models ( 6 hrs )


6.1 Recurrent Neural Networks
6.2 Back-propagation through time
6.3 Challenge - Exploding - Vanishing gradient and Gates
6.4 Popular RNN architectures
6.5 Applications of RNNs

7 Attention Mechanism (4 hrs)


7.1 Attention Pooling
7.2 Attention Scoring Functions
7.3 Multi-Head Attention, Self-Attention and Positional Encoding
7.4 Transformer architecture
7.5 Applications of Transformers

8 Neural Network search (2 hrs)


8.1 Search Space
8.2 Search algorithms
8.3 Evaluation Strategy

9 Time series Modelling and Forecasting ( 2 hrs)


9.1 Univariate, Multivariate and Multi-step CNN Models
9.2 Univariate, Multivariate and Multi-step LSTM Models

10 Other Learning Techniques (4 hrs)


10.1 Federated learning
10.2 Meta learning
10.3 Online (incremental) learning
Learning Outcomes:

No Learning Outcomes

LO1 Able to understand the basics of Deep Learning.

LO2 Able to understand and apply techniques related to Deep Learning to


applications.

LO3 Able to identify appropriate tools to implement the solutions to problems related
to Deep Learning and implement solutions.

Part B: Learning Plan

Session
Topic Title Resource Reference
No.

1 Fundamentals of Neural Network


 Objective of the course
 Why Deep Learning?
 Applications of Deep Learning
T1 – Ch1
 Biological neuron vs artificial neuron http://mlsp.cs.cmu.edu/
 Connectionism model people/rsingh/docs/
Chapter1_Introduction.pdf
 Perceptron
 Perceptron learning algorithm
 XOR Problem

2 Fundamentals of Neural Network http://mlsp.cs.cmu.edu/


people/rsingh/docs/
 Multilayer Perceptron (MLP), Chapter1_Introduction.pdf
 MLP on Boolean, reals and continuous values
 MLP as classifiers http://mlsp.cs.cmu.edu/
people/rsingh/docs/
 MLP as Universal approximators Chapter2_UniversalApproximat
 Issue of Depth and Width ors.pdf

3 Deep Feedforward Neural Network T1 – Ch4 and Ch3.4


 MLP with hidden Layers
 Forward Propagation
 Backward Propagation (review)
 Training a DNN using Gradient Descent algorithm
(review)
 Computational Graphs (review as already
discussed in MFML)

4 Deep Feedforward Neural Network


 Activation Functions T1 – Ch4 and Ch3.4
 Softmax Regression

5 Optimization algorithms for Deep models


 Challenges – Saddle points and plateau
 Non-convex optimization intuition
 Stochastic Gradient Descent (SGD), Minibatch SGD
T1 – Ch11
 Overview of Rprop, Quickprop
 Momentum, Nastrov’s Accelarated Momentum
 Algorithms with Adaptive Learning Rates, Adagrad,
RMSprop, ADAM

6 Regularization for Deep models


 Model Selection, Underfitting, and Overfitting
 L1 and L2 Regularization
 Dropout
T1 – Ch4 , 7.5
 Challenge - Vanishing and Exploding Gradients
 Parameter Initialization
 Challenge Covariance Shift
 Batch Normalization

7 Convolutional Neural Network


 Basics of Computer Vision and Invariance
 Convolutions for Images
 Learning a Kernel
T1 – Ch6
 Padding and stride
 Channels
 Pooling
 Designing a CNN

8 Popular CNN architectures T1 – Ch7


 LeNet
 AlexNet
 VGG16
 RCNN and Fast RCNN
 Network in Network (NiN)
 Inception Net
 ResNet
 DenseNet
 Transfer Learning
 Applications of CNN

9 Sequence Models
 Recurrent Neural Networks
 Types of Sequences and RNNs
T1 – Ch8
 Back-propagation Through Time (discuss the
paper)
 Gates and Exploding / Vanishing gradient

10 Popular RNN architectures


 Gated Recurrent Units (GRU)
 Long Short-Term Memory (LSTM) Networks T1 – Ch9
(discuss why and how LSTM solves)
 Bidirectional models

11 Attention Mechanism
 Attention Pooling
 Attention Scoring Functions T1 – Ch10
 Multi-Head Attention

12 Attention Mechanism
 Self-Attention
 Positional Encoding
T1 – Ch10
 Transformer architecture
 Applications of Transformers

13 Neural Network search overview


 Search Space
R5
 Search algorithms
 Evaluation Strategy

14 Time series Modelling and Forecasting R4


 Using CNN Ch-8, Ch-9
 Using LSTM
(Trends and Seasonality will be discussed. No overview of
statistical techniques)

15 https://arxiv.org/pdf/
1902.04885.pdf
Federated learning https://arxiv.org/pdf/
1903.10635.pdf
 Federated Learning Of Out-Of-Vocabulary Words
https://arxiv.org/pdf/
Meta learning 2004.05439.pdf

16 Online (incremental) learning https://arxiv.org/pdf/


1802.07569.pdf
 Continual Lifelong Learning with Neural Networks https://arxiv.org/pdf/
1904.07734v1.pdf
 Three scenarios for continual learning

Detailed Plan for Lab work

Session
Lab No. Lab Objective Lab Sheet Access URL
Reference

1 Introduction to Tensorflow, Keras 2

2 Computational graph in Pytorch 3

Deep Neural Network with Back-propagation


3 4
and optimization

4 CNN 6

5 RNN 9

6 LSTM 10

7 Transformers 12

8 Time series forecasting 15


Evaluation Scheme:
Legend: EC = Evaluation Component; AN = After Noon Session; FN = Fore Noon Session

No Name Type Duration Weight Day, Date, Session, Time

EC-1(a) Quizzes Online 10%

EC-1(b) Assignments Online 20%

EC-2 Mid-Semester Test Closed Book 30%

EC-3 Comprehensive Exam Open Book 40%

Note:
Syllabus for Mid-Semester Test (Closed Book): Topics in Session Nos. 1 to 8
Syllabus for Comprehensive Exam (Open Book): All topics (Session Nos. 1 to 16)

Important links and information:

Elearn portal: https://elearn.bits-pilani.ac.in or Canvas


Students are expected to visit the Elearn portal on a regular basis and stay up to date with
the latest announcements and deadlines.

Contact sessions: Students should attend the online lectures as per the schedule
provided on the Elearn portal.

Evaluation Guidelines:
1 EC-1a consists of two Quizzes. Students will attempt them through the course
pages on the Elearn portal. Announcements will be made on the portal, in a timely
manner.
2 EC-1b consists of two Assignments. Students will attempt them through the course
pages on the Elearn portal. Announcements will be made on the portal, in a timely
manner.
3 For Closed Book tests: No books or reference material of any kind will be
permitted. Use of calculators is permitted in all exams.
4 For Open Book exams: Use of books and any printed / written reference material
(filed or bound) is permitted. However, loose sheets of paper will not be allowed.
Use of calculators is permitted in all exams. Laptops/Mobiles of any kind are not
allowed. Exchange of any material is not allowed.
5 If a student is unable to appear for the Regular Test/Exam due to genuine
exigencies, the student should follow the procedure to apply for the Make-Up
Test/Exam which will be made available on the Elearn portal. The Make-Up
Test/Exam will be conducted only at selected exam centers on the dates to be
announced later.

It shall be the responsibility of the individual student to be regular in maintaining the self-
study schedule as given in the course hand-out, attend the online lectures, and take all the
prescribed evaluation components such as Assignment/Quiz, Mid-Semester Test and
Comprehensive Exam according to the evaluation scheme provided in the hand-out.

You might also like