Scribd
Upload
53 views1 page

Deep Learning Syllabus

The document outlines a 4-credit course on Deep Learning, covering key concepts, architectures, and applications of neural networks. It includes five units focusing on artificial neural networks, deep neural networks, convolutional neural networks, recurrent neural networks, and deep learning tools. The course aims to equip students with the ability to analyze and develop applications using deep learning technologies.

Uploaded by

piyush.kushwaha.ug22
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
53 views1 page

Deep Learning Syllabus

The document outlines a 4-credit course on Deep Learning, covering key concepts, architectures, and applications of neural networks. It includes five units focusing on artificial neural networks, deep neural networks, convolutional neural networks, recurrent neural networks, and deep learning tools. The course aims to equip students with the ability to analyze and develop applications using deep learning technologies.

Uploaded by

piyush.kushwaha.ug22
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

Course No.

Title of the Course Credits Course Pre-Requisite


Structure
Deep Learning 4 L-T-P ML and AI
3-1-0
COURS OUTCOMES (CO)

After completing the course, the students shall be able to:


CO1: To understand the basic concepts of deep learning.
CO2: To analyse deep neural networks
CO3: To analyse various deep CNN architectures
CO4: To understand various types of Neural Networks
CO5: To develop various applications of deep learning technologies.

Unit 1 Introduction to ANN, structure and working of Biological Neural Network ,


History of neural network research, Architecture of feed forward network,
single layer ANN, multi layer perceptron, back propagation learning, hidden
and output layer computation, back propagation learning

Unit 2 Deep neural networks (DNNs): Optimization for training DNNs, Newer optimization
methods for neural networks:AdaGrad, RMSProp, Adam. Regularization methods ,
dropout, drop connect, batch normalization.

Unit 3 Convolution neural networks (CNNs): Introduction to CNNs – convolution, pooling,


Deep CNN architectures – LeNet, AlexNet, VGG,Training CNNs:weights
initialization, batch normalization.

Unit 4 Recurrent neural networks (RNNs): Sequence modelling using RNNs, Back
propagation through time, Long Short Term Memory (LSTM), Bidirectional LSTMs,
Bidirectional RNNs, Gated RNN Architecture
Unit 5 Studies of deep-learning tools: TensorFlow, Keras, PyTorch, Deep learning
applications in image processing, Image segmentation, object detection, speech
recognition, image recognition and recommendation systems.

Text Books:

1. Ian Goodfellow, YoshuaBengio and Aaron Courville, Deep learning, In


preparation for MIT Press, Available online: http://www.deeplearningbook.org,
2016
2. Bengio, Yoshua. "Learning deep architectures for AI." Foundations and trends in
Machine Learning 2.1 (2009)

Reference Books:

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

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

You might also like