Neural Networks and Deep Learning


Neural Networks and Deep Learning, Springer, September 2018

Charu C. Aggarwal.

Book on neural networks and deep learning Table of Contents

Buy hardcover from Springer or Amazon (Free for computers connected to subscribing institutions only)

Buy hard-cover or PDF (for general public)

Buy low-cost paperback edition (Instructions for computers connected to subscribing institutions only)

This is an comprehensive textbook on neural networks and deep learning. The following aspects are covered:

The basics of neural networks: Chapters 1 and 2 discuss the basics of neural network design and also the fundamentals of training them. The simulation of various machine learning models with neural networks is provided. Examples include least-squares regression, SVMs, logistic regression, Widrow-Hoff learning, singular value decomposition, and recommender systems. Recent models like word2vec are also explored, together with their connections with traditional matrix factorization. Exploring the interface between machine learning and neural networks is important because it provides a deeper understanding of how neural networks generalize known machine learning methods, and the cases in which neural networks have advantages over traditional machine learning.

Challenges in training neural networks: Although Chapters 1 and 2 provide an overview of the training methods for neural networks, a more detailed understanding of the training challenges is provided in Chapters 3 and 4. In particular, issues related to network depth and also overfitting are discussed. Chapter 5 presents a classical architecture, referred to as radial-basis function networks, which is no longer used frequently.

Advanced architectures and applications: A lot of the success in neural network design is a result of the specialized architectures for various domains and applications. Examples of such specialized architectures include recurrent neural networks and convolutional neural networks. Since the specialized architectures form the key to the understanding of neural network performance in various domains, most of the book will be devoted to this setting. Several advanced topics like deep reinforcement learning, neural Turing mechanisms, and generative adversarial networks are discussed.

Some of the ``forgotten'' architectures like RBF networks and Kohonen self-organizing maps are included because of their potential in many applications. The book is written for graduate students, researchers, and practitioners. The book does require knowledge of probability and linear algebra. Furthermore basic knowledge of machine learning is helpful. Numerous exercises are available along with a solution manual to aid in classroom teaching. Where possible, an application-centric view is highlighted in order to give the reader a feel for the technology.


Cost-effective methods for obtaining electronic and hardcopy versions

The book is available in both hardcopy (hardcover) and electronic versions. The hardcover is available at all the usual channels (e.g, Amazon, Barnes and Noble etc.), in Kindle format, and also directly from Springer in hardcopy and pdf format. The good thing about Springer is that electronic versions are often widely accessible at no cost to subscribing institutions, which is particularly convenient for students. My understanding is that a very large fraction of universities in North America, Europe, Australia, and New Zealand are subscribers, and a rapidly increasing number of universities in Asia are also subscribing. The electronic version is available at the following Springerlink pointer . For subscribing institutions click from a computer directly connected to your institution network to download the book for free. Springer uses the domain name of your computer to regulate access. To be eligible, your institution must subscribe to "e-book package english (Computer Science)" or "e-book package english (full collection)". If your institution is eligible, you will see a (free) `Download Book' button. Otherwise you will see a (paid) `Get Access' button. Sometimes you may be able to download it from your library e-collection, even when it is not Web-accessible from your institution. For those who prefer desk copies rather than electronic books, there are some very cost-effective methods to obtain a paperback MyCopy edition for $25 or less (subscribing institutions only). If you have ever published an article (even journal) with Springer, you are also entitled to an additional 40% author discount for any Springer book (including the $25 paperback edition) using the approach described here .


About the Author

Charu Aggarwal is a Distinguished Research Staff Member (DRSM) at the IBM T. J. Watson Research Center in Yorktown Heights, New York. He completed his B.Tech. from IIT Kanpur in 1993 and his Ph.D. from Massachusetts Institute of Technology in 1996. He has worked extensively in the field of data mining, with particular interests in data streams, privacy, uncertain data and social network analysis. He has published 17 (6 authored and 11 edited) books, over 350 papers in refereed venues, and has applied for or been granted over 80 patents. His h-index is 80. Because of the commercial value of the above-mentioned patents, he has received several invention achievement awards and has thrice been designated a Master Inventor at IBM. He is a recipient of an IBM Corporate Award (2003) for his work on bio-terrorist threat detection in data streams, a recipient of the IBM Outstanding Innovation Award (2008) for his scientific contributions to privacy technology, and two IBM Outstanding Technical Achievement Awards for his work on streaming systems and high-dimensional data analysis. He has received two best paper awards and an EDBT Test-of-Time Award (2014). He has received the IEEE ICDM Research Contributions Award (2015), which is one of two highest awards for research in the field of data mining. He has served as the general or program co-chair of the IEEE Big Data Conference (2014), the ICDM Conference (2015), the ACM CIKM Conference (2015), and the KDD Conference (2016). He also co-chaired the data mining track at the WWW Conference 2009. He served as an associate editor of the IEEE Transactions on Knowledge and Data Engineering from 2004 to 2008. He is an associate editor of the ACM Transactions on Knowledge Discovery and Data Mining Journal , an action editor of the Data Mining and Knowledge Discovery Journal , an associate editor of the IEEE Transactions on Big Data, and an associate editor of the Knowledge and Information Systems Journal. He is and editor-in-chief of the ACM Transactions on Knowledge Discovery from Data, and is also an editor-in-chief of the ACM SIGKDD Explorations. He is a fellow of the SIAM (2015), ACM (2013) and the IEEE (2010) for "contributions to knowledge discovery and data mining techniques."


Solution Manual for Book

The solution manual for the book is available here from Springer. There is a link for the solution manual on this page. If you are an instructor, then you can obtain a copy. Please do not ask me directly for a copy of the solution manual. It can only be distributed by Springer.


Resources for book

I have latex slides that can be used for teaching as well as video lectures for the book. The entire slide deck as a PDF is here The source for the latex slides is available here [after book release] together with ppt figures. Your are free to use ppt figures in your own slides, but you must credit the book. Use of figures in another publication requires permission from Springer through copyright clearance center.

Chapter 1: An Introduction to Neural Networks

Slides PDF

Latex source of slides and figures

Chapter 2: Machine Learning with Shallow Neural Networks

Slides PDF

Latex source of slides and figures

Chapter 3: Training Deep Neural Networks

Slides PDF

Latex source of slides and figures

Chapter 4: Teaching Deep Learners to Generalize

Slides PDF

Latex source of slides and figures

Chapter 5: Radial Basis Function Networks

Slides PDF

Latex source of slides and figures

Chapter 6: Restricted Boltzmann Machines

Slides PDF

Latex source of slides and figures

Chapter 7: Recurrent Neural Networks

Slides PDF

Latex source of slides and figures

Chapter 8: Convolutional Neural Networks

Slides PDF

Latex source of slides and figures

Chapter 9: Deep Reinforcement Learning

Slides PDF

Latex source of slides and figures

Chapter 10: Advancement Topics in Deep Learning

Slides PDF

Latex source of slides and figures