Provides a comprehensive and up-to-date overview of deep learning by discussing a range of methodological and algorithmic issues
Addresses implementations and case studies, identifying the best design practices and assessing business models and methodologies encountered in industry, health care, science, administration, and business
Serves as a unique and well-structured reference resource for graduate and senior undergraduate students in areas such as computational intelligence, pattern recognition, computer vision, knowledge acquisition and representation, and knowledge-based systems
This book offers a timely reflection on the remarkable range of algorithms and applications that have made the area of deep learning so attractive and heavily researched today. Introducing the diversity of learning mechanisms in the environment of big data, and presenting authoritative studies in fields such as sensor design, health care, autonomous driving, industrial control and wireless communication, it enables readers to gain a practical understanding of design. The book also discusses systematic design procedures, optimization techniques, and validation processes.
Preface.- Chapter 1. Direct Error Driven Learning for Classification in Applications Generating Big-Data.- Chapter 2. Deep Learning for Soft Sensor Design.- Chapter 3. Case Study: Deep Convolutional Networks in Healthcare, etc.
Inhaltsverzeichnis
Preface.- Chapter 1. Direct Error Driven Learning for Classification in Applications Generating Big-Data.- Chapter 2. Deep Learning for Soft Sensor Design.- Chapter 3. Case Study: Deep Convolutional Networks in Healthcare, etc.
Klappentext
This book offers a timely reflection on the remarkable range of algorithms and applications that have made the area of deep learning so attractive and heavily researched today. Introducing the diversity of learning mechanisms in the environment of big data, and presenting authoritative studies in fields such as sensor design, health care, autonomous driving, industrial control and wireless communication, it enables readers to gain a practical understanding of design. The book also discusses systematic design procedures, optimization techniques, and validation processes.
Provides a comprehensive and up-to-date overview of deep learning by discussing a range of methodological and algorithmic issues
Addresses implementations and case studies, identifying the best design practices and assessing business models and methodologies encountered in industry, health care, science, administration, and business
Serves as a unique and well-structured reference resource for graduate and senior undergraduate students in areas such as computational intelligence, pattern recognition, computer vision, knowledge acquisition and representation, and knowledge-based systems
