book

Deep Learning

Name: Deep Learning
ISBN: 9783110670929

by Siddhartha Bhattacharyya, Vaclav Snasel, Aboul Ella Hassanien, Satadal Saha, B. K. Tripathy

June 2020

Intermediate to advanced

161 pages

5h 27m

English

De Gruyter

Read now

Unlock full access

Dedication
Preface List of Contributors
Soumyajit Goswami 1 Deep Learning – A State-of-the-Art Approach to Artificial Intelligence
1.1 Introduction1.2 AI versus ML versus DL1.3 Artificial neural network1.3.1 Classification of ANN1.3.2 ANN learning1.4 Deep learning1.4.1 What makes DL state of the art?1.4.2 Activation functions1.4.3 Popular DL architectures1.5 ML platforms of multiple organizations1.6 IBM Watson Studio (formerly, Data Science Experience)1.7 Conclusion
Karan Maheshwari, Aditya Shaha, Dhruv Arya, Rajkumar Rajasekaran, B. K. Tripathy 2 Convolutional Neural Networks: A Bottom-Up Approach
2.1 Introduction2.2 The convolutional operation2.3 Relationships between input dimension, output dimension, and the filter dimension2.4 Properties of CNNs2.4.1 Sparse connections2.4.2 Receptive fields2.4.3 Parameter sharing2.4.4 Equivariance to translation2.5 Building a CNN2.5.1 Pooling in CNN2.5.2 Building block of CNN2.6 Complete CNN2.6.1 Le-Net architecture2.7 What is the network learning?2.7.1 Visualizing the first layer2.7.2 Saliency maps2.8 Transposed convolution2.9 Applications of CNN2.10 Conclusion and future work
Ranjan Jana, Siddhartha Bhattacharyya, Swagatam Das 3 Handwritten Digit Recognition Using Convolutional Neural Networks
3.1 Introduction3.2 Motivation for handwritten digit recognition3.3 Related work3.4 Overview of MLP, CNN, and RNN3.4.1 Multilayer perceptron3.4.2 Convolutional neural network3.4.3 Recurrent neural network3.5 Implementation3.5.1 Database used3.5.2 Design of proposed CNN architecture3.6 Experimental result3.7 Conclusion
Amit Adate, Dhruv Arya, Aditya Shaha, B. K. Tripathy 4 Impact of Deep Neural Learning on Artificial Intelligence Research
4.1 Introduction4.2 Convolutional neural models4.3 Recurrent neural networks4.4 Generative adversarial networks4.5 Variational autoencoders4.6 Deep reinforcement learning4.6.1 Deep Q-networks4.7 Making deep learning work4.7.1 Regularization4.7.2 Transfer learning4.8 Deep learning frameworks4.9 Engineering applications of deep learning4.10 Conclusion
Rajib Saha, Anirban Mukherjee, Avik Sarkar, Shatabhisa Dey 5 Extraction of Common Feature of Dysgraphia Patients by Handwriting Analysis Using Variational Autoencoder
5.1 Introduction5.2 Background5.3 Proposed work and methodology5.3.1 Preprocessing5.3.2 Line segmentation5.3.3 Word segmentation5.3.4 Character segmentation5.3.5 Implementation of VAE5.4 Results and discussion5.4.1 Line segmentation output5.4.2 Word segmentation output5.4.3 Character segmentation output5.4.4 Output of reconstruction using VAE5.5 Conclusion
Ankita Bose, B. K. Tripathy 6 Deep Learning for Audio Signal Classification
6.1 Introduction6.2 Audio signal processing and its importance6.2.1 Audio signals6.2.2 Feature extraction methods6.2.3 Mel frequency cepstral coefficients (MFCCs)6.3 Timeline of algorithms used for audio signal processing and classification6.3.1 Hidden Markov models6.3.2 Long short-term memory-recurrent neural networks6.3.3 Restricted Boltzman machines with deep belief networks6.3.4 WaveNets6.4 Current applications6.4.1 Speech to text converter6.4.2 Audio classification6.4.3 Speech and music generation6.4.4 Language translation6.4.5 Personal assistants6.5 Future scope6.6 Conclusion
Mahua Bose, Kalyani Mali 7 Backpropagation Through Time Algorithm in Temperature Prediction
7.1 Introduction7.2 Basic concept of backpropagation through time7.3 Proposed method7.4 Experimental results and discussion7.4.1 Description of datasets7.4.2 Performance evaluation7.5 Conclusion
Index

Content preview from Deep Learning

6 Deep Learning for Audio Signal Classification

Ankita Bose

VIT University, Vellore, Tamil Nadu, India

B. K. Tripathy

VIT University, Vellore, Tamil Nadu, India

Abstract

Audio signal processing and its classification dates back to the past century. From speech recognition to speaker recognition and from speech to text conversion to music generation, a lot of advances has been made in this field using algorithms such as hidden Markov models, recurrent neural networks with long short-term memory layers (LSTM), deep convolutional neural networks (DCNNs), and the recent state-of-the-art model for music and speech generation using WaveNets. These algorithms are applied after the audio signals are processed and effective feature extraction ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Publisher Resources

ISBN: 9783110670929

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Deep Learning

by Siddhartha Bhattacharyya, Vaclav Snasel, Aboul Ella Hassanien, Satadal Saha, B. K. Tripathy