Provides engineers and researchers with clear methodologies for taking advantage of neural networks in industrial, financial or banking applications
Scientists
Neural networks represent a powerful data processing technique that has reached maturity. When clearly understood and appropriately used, they are a mandatory component in the toolbox of any engineer who wants make the best use of the available data, in order to build models, make predictions, mine data, recognize shapes or signals, etc. Ranging from theoretical foundations to real-life applications, this book is intended to provide engineers and researchers with clear methodologies for taking advantage of neural networks in industrial, financial or banking applications, many instances of which are presented in the book. For the benefit of readers wishing to gain deeper knowledge of the topics, the book features appendices that provide theoretical details for greater insight, and algorithmic details for efficient programming and implementation.
Neural Networks: An Overview.- Modeling with Neural Networks: Principles and Model Design Methodology.- Modeling Metholodgy: Dimension Reduction and Resampling Methods.- Neural Identification of Controlled Dynamical Systems and Recurrent Networks.- Closed-Loop Control Learning.- Discrimination.- Self-Organizing Maps and Unsupervised Classification.- Neural Networks without Training for Optimization.
Neural networks represent a powerful data processing technique that has reached maturity and broad application. When clearly understood and appropriately used, they are a mandatory component in the toolbox of any engineer who wants make the best use of the available data, in order to build models, make predictions, mine data, recognize shapes or signals, etc. Ranging from theoretical foundations to real-life applications, this book is intended to provide engineers and researchers with clear methodologies for taking advantage of neural networks in industrial, financial or banking applications, many instances of which are presented in the book. For the benefit of readers wishing to gain deeper knowledge of the topics, the book features appendices that provide theoretical details for greater insight, and algorithmic details for efficient programming and implementation. The chapters have been written by experts ands seemlessly edited to present a coherent and comprehensive, yet not redundant, practically-oriented introduction.
From the reviews:
"Artificial neural networks (ANN) generated fascinating dreams of solving problems in complex systems ... . The present book, contributed to by several authors, provides a clear deillegalscription with statistical analysis for ANN, together with examples to show the power and advantages of ANN. Comparisons of ANN to traditional statistical methods, such as linear regressions, the Bayes statistics, etc. are also dealt with. This will greatly help readers to understand the principles and to use ANN correctly to develop significant applications." (Min Ping Qian, Mathematical Reviews, Issue 2007 a)
"We are nowadays looking at ANNs as a machine learning tool offering a wide range of possibilities in the modeling and ordering of data, in signal processing, adaptive control, and many other fields. The book offers a systematic, thorough and understandable introduction to this field. ... the book is a useful introduction for engineers and researchers in the field of modeling, data processing, control, machine learning, optimization, and related fields." (Andreas Schierwagen, Zentralblatt MATH, Vol. 1119 (21), 2007)
Neural networks represent a powerful data processing technique that has reached maturity and broad application. When clearly understood and appropriately used, they are a mandatory component in the toolbox of any engineer who wants make the best use of the available data, in order to build models, make predictions, mine data, recognize shapes or signals, etc. Ranging from theoretical foundations to real-life applications, this book is intended to provide engineers and researchers with clear methodologies for taking advantage of neural networks in industrial, financial or banking applications, many instances of which are presented in the book. For the benefit of readers wishing to gain deeper knowledge of the topics, the book features appendices that provide theoretical details for greater insight, and algorithmic details for efficient programming and implementation. The chapters have been written by experts and edited to present a coherent and comprehensive, yet not redundant, practically oriented introduction.
From the reviews:
"Artificial neural networks (ANN) generated fascinating dreams of solving problems in complex systems ... . The present book, contributed to by several authors, provides a clear deillegalscription with statistical analysis for ANN, together with examples to show the power and advantages of ANN. Comparisons of ANN to traditional statistical methods, such as linear regressions, the Bayes statistics, etc. are also dealt with. This will greatly help readers to understand the principles and to use ANN correctly to develop significant applications." (Min Ping Qian, Mathematical Reviews, Issue 2007 a)
"We are nowadays looking at ANNs as a machine learning tool offering a wide range of possibilities in the modeling and ordering of data, in signal processing, adaptive control, and many other fields. The book offers a systematic, thorough and understandable introduction to this field. ... the book is a useful introduction for engineers and researchers in the field of modeling, data processing, control, machine learning, optimization, and related fields." (Andreas Schierwagen, Zentralblatt MATH, Vol. 1119 (21), 2007)
Über den Autor
Scientists
Inhaltsverzeichnis
Neural Networks: An Overview.- Modeling with Neural Networks: Principles and Model Design Methodology.- Modeling Metholodgy: Dimension Reduction and Resampling Methods.- Neural Identification of Controlled Dynamical Systems and Recurrent Networks.- Closed-Loop Control Learning.- Discrimination.- Self-Organizing Maps and Unsupervised Classification.- Neural Networks without Training for Optimization.
Klappentext
Neural networks represent a powerful data processing technique that has reached maturity and broad application. When clearly understood and appropriately used, they are a mandatory component in the toolbox of any engineer who wants make the best use of the available data, in order to build models, make predictions, mine data, recognize shapes or signals, etc. Ranging from theoretical foundations to real-life applications, this book is intended to provide engineers and researchers with clear methodologies for taking advantage of neural networks in industrial, financial or banking applications, many instances of which are presented in the book. For the benefit of readers wishing to gain deeper knowledge of the topics, the book features appendices that provide theoretical details for greater insight, and algorithmic details for efficient programming and implementation. The chapters have been written by experts and edited to present a coherent and comprehensive, yet not redundant, practically oriented introduction.
Neural networks represent a powerful data processing technique that has reached maturity. When clearly understood and appropriately used, they are a mandatory component in the toolbox of any engineer who wants make the best use of the available data, in order to build models, make predictions, mine data, recognize shapes or signals, etc. Ranging from theoretical foundations to real-life applications, this book is intended to provide engineers and researchers with clear methodologies for taking advantage of neural networks in industrial, financial or banking applications, many instances of which are presented in the book. For the benefit of readers wishing to gain deeper knowledge of the topics, the book features appendices that provide theoretical details for greater insight, and algorithmic details for efficient programming and implementation.
