Neural Networks and Deep Learning - A Textbook

This book covers both classical and modern models in deep learning. The primary focus is on the theory and algorithms of deep learning. The theory and algorithms of neural networks are particularly important for understanding important concepts, so that one can understand the important design concepts of neural architectures in different applications. Why do neural networks work? When do they work better than off-the-shelf machine-learning models? When is depth useful? Why is training neural networks so hard? What are the pitfalls? The book is also rich in discussing different applications in order to give the practitioner a flavor of how neural architectures are designed for different types of problems. Deep learning methods for various data domains, such as text, images, and graphs are presented in detail. The chapters of this book span three categories:
 
The basics of neural networks: The backpropagation algorithm is discussed in Chapter 2.
Many traditional machine learning models can be understood as special cases of neural networks. Chapter 3 explores the connections between traditional machine learning and neural networks. Support vector machines, linear/logistic regression, singular value decomposition, matrix factorization, and recommender systems are shown to be special cases of neural networks.
 
Fundamentals of neural networks:  A detailed discussion of training and regularization is provided in Chapters 4 and 5. Chapters 6 and 7 present radial-basis function (RBF) networks and restricted Boltzmann machines.
 
Advanced topics in neural networks:  Chapters 8, 9, and 10 discuss recurrent neural networks, convolutional neural networks, and graph neural networks. Several advanced topics like deep reinforcement learning, attention mechanisms, transformer networks, Kohonen self-organizing maps, and generative adversarial networks are introduced in Chapters 11 and 12.
 
The textbook is written for graduate students and upper under graduate level students. Researchers and practitioners working within this related field will want to purchase this as well.
Where possible, an application-centric view is highlighted in order to provide an understanding of the practical uses of each class of techniques.
The second edition is substantially reorganized and expanded with separate chapters on backpropagation and graph neural networks. Many chapters have been significantly revised over the first edition.
Greater focus is placed on modern deep learning ideas such as attention mechanisms, transformers, and pre-trained language models.

Table des matières

An Introduction to Neural Networks.- The Backpropagation Algorithm.- Machine Learning with Shallow Neural Networks.- Deep Learning: Principles and Training Algorithms.- Teaching a Deep Neural Network to Generalize.- Radial Basis Function Networks.- Restricted Boltzmann Machines.- Recurrent Neural Networks.- Convolutional Neural Networks.- Graph Neural Networks.- Deep Reinforcement Learning.- Advanced Topics in Deep Learning.

A propos de l'auteur

Charu C. Aggarwal is a Distinguished Research Staff Member (DRSM) at the IBM T. J. Watson Research Center in Yorktown Heights, New York. He completed his undergraduate degree in Computer Science from the Indian Institute of Technology at Kanpur in 1993 and his Ph.D. in Operations Research from the Massachusetts Institute of Technology in 1996. He has published more than 400 papers in refereed conferences and journals, and has applied for or been granted more than 80 patents. He is author or editor of 20 books, including textbooks on linear algebra, machine learning (for text), neural networks, recommender systems, and outlier analysis. Because of the commercial value of his patents, he has thrice been designated a Master Inventor at IBM. He has received several internal and external awards, including the EDBT Test-of-Time Award (2014), the ACM SIGKDD Innovation Award (2019), and the IEEE ICDM Research Contributions Award (2015). He is also a recipient of the W. Wallace McDowell Award, which is the highest technical honor given by IEEE Computer Society in the field of computer science. He has served as an editor-in-chief of the ACM SIGKDD Explorations. He is currently serving as the editor-in-chief of the ACM Transactions on Knowledge Discovery from Data and as an editor-in-chief of ACM Books. He is a fellow of the SIAM, ACM, and the IEEE, for "contributions to knowledge discovery and data mining algorithms."

Résumé

This book covers both classical and modern models in deep learning. The primary focus is on the theory and algorithms of deep learning. The theory and algorithms of neural networks are particularly important for understanding important concepts, so that one can understand the important design concepts of neural architectures in different applications. Why do neural networks work? When do they work better than off-the-shelf machine-learning models? When is depth useful? Why is training neural networks so hard? What are the pitfalls? The book is also rich in discussing different applications in order to give the practitioner a flavor of how neural architectures are designed for different types of problems. Deep learning methods for various data domains, such as text, images, and graphs are presented in detail. The chapters of this book span three categories:

 

The basics of neural networks:
 The backpropagation algorithm is discussed in Chapter 2.

Many traditional machine learning models can be understood as special cases of neural networks. Chapter 3 explores the connections between traditional machine learning and neural networks. Support vector machines, linear/logistic regression, singular value decomposition, matrix factorization, and recommender systems are shown to be special cases of neural networks.
 
Fundamentals of neural networks:
  A detailed discussion of training and regularization is provided in Chapters 4 and 5. Chapters 6 and 7 present radial-basis function (RBF) networks and restricted Boltzmann machines.


 

Advanced topics in neural networks:
  Chapters 8, 9, and 10 discuss recurrent neural networks, convolutional neural networks, and graph neural networks. Several advanced topics like deep reinforcement learning, attention mechanisms, transformer networks, Kohonen self-organizing maps, and generative adversarial networks are introduced in Chapters 11 and 12.

 
The textbook is written for graduate students and upper under graduate level students. Researchers and practitioners working within this related field will want to purchase this as well.
Where possible, an application-centric view is highlighted in order to provide an understanding of the practical uses of each class of techniques.

The second edition is substantially reorganized and expanded with separate chapters on backpropagation and graph neural networks. Many chapters have been significantly revised over the first edition.

Greater focus is placed on modern deep learning ideas such as attention mechanisms, transformers, and pre-trained language models.

Détails du produit

• Auteurs: Charu C Aggarwal, Charu C. Aggarwal
• Edition: Springer, Berlin
• Langues: Anglais
• Format d'édition: Livre Relié
• Sortie: 24.07.2023
• EAN: 9783031296413
• ISBN: 978-3-0-3129641-3
• Pages: 529
• Dimensions: 179 mm x 36 mm x 260 mm
• Illustrations: XXIV, 529 p. 150 illus., 22 illus. in color.
• Catégories: Sciences naturelles, médecine, informatique, technique > Informatique, ordinateurs > Informatique; B, Künstliche Intelligenz, machine learning, Data Mining, Artificial Intelligence, Natürliche Sprachen und maschinelle Übersetzung, Wissensbasierte Systeme, Expertensysteme, Mathematics and Statistics, Data Mining and Knowledge Discovery, Expert systems / knowledge-based systems, Natural Language Processing (NLP), Natural language processing (Computer science), Knowledge based Systems, Natural language and machine translation, Expert systems (Computer science)