Deep Learning Applications, Volume 3

by M. Arif Wani (Editor), Bhiksha Raj (Editor), Feng Luo (Editor), Dejing Dou (Editor)

Overview

This book presents a compilation of extended version of selected papers from the 19th IEEE International Conference on Machine Learning and Applications (IEEE ICMLA 2020) and focuses on deep learning networks in applications such as pneumonia detection in chest X-ray images, object detection and classification, RGB and depth image fusion, NLP tasks, dimensionality estimation, time series forecasting, building electric power grid for controllable energy resources, guiding charities in maximizing donations, and robotic control in industrial environments. Novel ways of using convolutional neural networks, recurrent neural network, autoencoder, deep evidential active learning, deep rapid class augmentation techniques, BERT models, multi-task learning networks, model compression and acceleration techniques, and conditional Feature Augmented and Transformed GAN (cFAT-GAN) for the above applications are covered in this book. Readers will find insights to help them realize novel waysof using deep learning architectures and algorithms in real-world applications and contexts, making the book an essential reference guide for academic researchers, professionals, software engineers in the industry, and innovative product developers.

Product Details

ISBN-13:	9789811633560
Publisher:	Springer Nature Singapore
Publication date:	11/13/2021
Series:	Advances in Intelligent Systems and Computing , #1395
Edition description:	1st ed. 2022
Pages:	322
Product dimensions:	6.10(w) x 9.25(h) x (d)

About the Author

Dr. M. Arif Wani is Professor at the University of Kashmir, having previously served as Professor at California State University, Bakersfield. He completed his M. Tech. in Computer Technology at the Indian Institute of Technology, Delhi, and his Ph.D. in Computer Vision at Cardiff University, UK. His research interests are in the area of machine learning, with a focus on neural networks, deep learning, inductive learning, and support vector machines, and with application to areas that include computer vision, pattern recognition, classification, prediction and analysis of gene expression datasets. He has published many papers in reputed journals and conferences in these areas. Dr. Wani has co-authored the book ‘Advances in Deep Learning’, co-edited many books in ‘Machine Learning and Applications’ and ‘Deep Learning Applications’. He is a member of many academic and professional bodies.

Dr. Bhiksha Raj is Professor in the School of Computer Science at Carnegie Mellon University, with additional affiliations to the Electrical Engineering and Machine Learning departments. He is Fellow of the IEEE. At CMU he leads the Machine Learning for Signal Processing group, which conducts research on Speech and Audio Processing, Machine Learning, Deep Learning, AI, and Security and Privacy Issues in Speech. He also teaches CMU’s flagship course on introduction to Deep Learning, a course simultaneously broadcast to multiple countries across the world, and attended by more than 2000 students from many universities and organizations around the world, each semester. He has authored or co-authored more than 300 scientific papers with over 12,000 citations and an H-index greater than 50 and holds numerous patents in the areas of signal processing, machine learning, privacy, audio and speech processing, and artificial intelligence.

Dr. Feng Luo currently is Professor at the School of Computing, Clemson University, and Founding Director of Clemson Artificial Intelligence Research Institute for Science and Engineering (AIRISE). He joined Clemson University in 2006. Before Clemson, He was Post-doctoral Senior Research Associate at the Department of Pathology of the University of Texas Southwestern Medical Center at Dallas. His research interests are machine learning/deep learning, bioinformatics, and big data analytics. He has published 58 journals and 30 conference papers in these areas. He holds a Ph.D. degree in Computer Science from the University of Texas at Dallas in 2004. He is Senior Member of IEEE.

Dejing Dou is Head of Big Data Lab (BDL) and Business Intelligence Lab (BIL) at Baidu Research. He is also Full Professor (on leave) from the Computer and Information Science Department at the University of Oregon and has led the Advanced Integration and Mining (AIM) Lab since 2005. He has been Director of the NSF IUCRC Center for Big Learning (CBL) since 2018. He was Visiting Associate Professor at Stanford Center for Biomedical Informatics Research during 2012–2013. Prof. Dou received his bachelor’s degree from Tsinghua University, China, in 1996 and his Ph.D. degree from Yale University in 2004. His research areas include artificial intelligence, data mining, data integration, NLP, and health informatics. Dejing Dou has published more than 100 research papers, some of which appear in prestigious conferences and journals like AAAI, IJCAI, ICML, NeurIPS, ICLR, KDD, ICDM, ACL, EMNLP, CIKM, ISWC, TKDD, JIIS, and JoDS, with more than 3500 Google Scholar citations. His DEXA'15 paper received the best paper award. His KDD'07 paper was nominated for the best research paper award. He is on the Editorial Boards of Journal on Data Semantics, Journal of Intelligent Information Systems, and PLOS ONE. He has been serving as program committee members for major international conferences and as program co-chairs for five of them. He has received over $5 million PI research grants from the NSF and the NIH. Dejing Dou is Senior Member of ACM and IEEE.

Table of Contents

Deep Rapid Class Augmentation; a New Progressive Learning Approach that Eliminates the Issue of Catastrophic Forgetting.- A Comprehensive Analysis of Subword Contextual Embeddings for Languages with Rich Morphology.- RGB and Depth Image Fusion for Object Detection using Deep Learning.- Dimension Estimation Using Autoencoders with Applications to Financial Market Analysis.- A New Clustering-Based Technique for the Acceleration of Deep Convolutional Networks.- Deep Learning based Time Series Forecasting.- DEAL: Deep Evidential Active Learning for Image Classification.- LB-CNN: Convolutional Neural Network with Latent Binarization for Large Scale Multi[1]class Classification.- Efficient Deployment of Deep Learning Models on Autonomous Robots in the ROS Environment.- Building Power Grid 2.0: Deep Learning and Federated Computations for Energy Decarbonization and Edge Resilience.- Improving the Donor Journey with Convolutional and Recurrent Neural Networks.