Scribd
Upload
48 views

CS671

1. This document provides details about the Deep Learning and Applications course offered at IIT Mandi. The course covers fundamental concepts in deep learning including artificial neural networks, feedforward neural networks, deep neural networks, convolutional neural networks, recurrent neural networks, and generative models. 2. The course is intended for undergraduate students in computer science and electrical engineering as well as graduate students. It carries 3 credits and has prerequisites in probability, random processes, and linear algebra. Students will implement and train neural networks and complete a project applying deep learning to solve a real-world problem. 3. The course is taught by Aditya Nigam and uses the online Deep Learning book as a primary textbook along with other references

Uploaded by

siuszeen
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
48 views

CS671

1. This document provides details about the Deep Learning and Applications course offered at IIT Mandi. The course covers fundamental concepts in deep learning including artificial neural networks, feedforward neural networks, deep neural networks, convolutional neural networks, recurrent neural networks, and generative models. 2. The course is intended for undergraduate students in computer science and electrical engineering as well as graduate students. It carries 3 credits and has prerequisites in probability, random processes, and linear algebra. Students will implement and train neural networks and complete a project applying deep learning to solve a real-world problem. 3. The course is taught by Aditya Nigam and uses the online Deep Learning book as a primary textbook along with other references

Uploaded by

siuszeen
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

IIT Mandi

Course Name: Deep Learning and Applications


Course code: CS671
Credits: 3-1-0-4
Prerequisites: Probability and Random Processes, Linear Algebra
Intended for: B.Tech, MS/PhD in the area.
Elective/Core: Discipline elective for B.Tech CSE and EE, free elective for others
Semester: Any semester
Faculty: Aditya Nigam
----------------------------------------------------------------------------------------------------------------
Preamble:
In the last decade due to availability of cheap computation, several neural network ap-
proaches had been explored in order to advance the performance of many state-of-the-art vis-
ual recognition problems such as image searching, understanding, medical applications, au-
tonomous vehicles such as drones and self-driving cars etc. All these problems relies of effi-
cient, accurate and robust solutions for basic vision tasks such like image classification, lo-
calization and detection. In this course students will be given an exposure to the details of
neural networks as well as deep learning architectures and to develop end-to-end models for
such tasks. Students will learn to implement, train and debug their own neural networks. This
is a project oriented practical course in which every student have to develop a complete
working model to solve some real world problem.
Course Modules:
1. Basics of artificial neural networks (ANN): Artificial neurons, Computational models
of neurons, Structure of neural networks, Functional units of ANN for pattern
recognition tasks [4 Hrs]

2. Feedforward neural networks: Pattern classification using perceprton, Multilayer


feedforward neural networks (MLFFNNs), Backpropagation learning, Empirical risk
minimization, Regularization, Autoencoders [6Hrs]

3. Deep neural networks (DNNs): Difficulty of training DNNs, Greedy layerwise


training, Optimization for training DNNs, Newer optimization methods for neural
networks (AdaGrad, RMSProp, Adam), Second order methods for training,
Regularization methods (dropout, drop connect, batch normalization) [12 Hrs]

4. Convolution neural networks (CNNs): Introduction to CNNs – convolution, pooling,


Deep CNNs, Different deep CNN architectures – LeNet, AlexNet, VGG, PlacesNet,
Training a CNNs: weights initialization, batch normalization, hyperparameter
optimization, Understanding and visualizing CNNs. [12 Hrs]

CS671 1
5. Recurrent neural networks (RNNs): Sequence modeling using RNNs, Back
propagation through time, Long Short Term Memory (LSTM), Bidirectional LSTMs,
Bidirectional RNNs, Gated RNN Architecture [8 Hrs]

6. Generative models: Restrictive Boltzmann Machines (RBMs), Stacking RBMs,


Belief nets, Learning sigmoid belief nets, Deep belief nets [8 Hrs]

7. Applications: Applications in vision, speech and natural language processing [6 Hrs]

Textbooks:
1. Ian Goodfellow, Yoshua Bengio and Aaron Courville, Deep learning, In preparation
for MIT Press, Available online: http://www.deeplearningbook.org, 2016

References:
1. S. Haykin, Neural Networks and Learning Machines , Prentice Hall of India, 2010

2. Satish Kumar, Neural Networks - A Class Room Approach, Second Edition, Tata
McGraw-Hill, 2013

3. B. Yegnanarayana, Artificial Neural Networks, Prentice- Hall of India, 1999

4. C.M. Bishop, Pattern Recognition and Machine Learning, Springer, 2006

CS671 2

You might also like