E-Book, Englisch, 570 Seiten
Samarasinghe Neural Networks for Applied Sciences and Engineering
Erscheinungsjahr 2006
ISBN: 978-1-4200-1306-1
Verlag: Taylor & Francis
Format: PDF
Kopierschutz: Adobe DRM (»Systemvoraussetzungen)
From Fundamentals to Complex Pattern Recognition
E-Book, Englisch, 570 Seiten
ISBN: 978-1-4200-1306-1
Verlag: Taylor & Francis
Format: PDF
Kopierschutz: Adobe DRM (»Systemvoraussetzungen)
In response to the exponentially increasing need to analyze vast amounts of data, Neural Networks for Applied Sciences and Engineering: From Fundamentals to Complex Pattern Recognition provides scientists with a simple but systematic introduction to neural networks.
Beginning with an introductory discussion on the role of neural networks in scientific data analysis, this book provides a solid foundation of basic neural network concepts. It contains an overview of neural network architectures for practical data analysis followed by extensive step-by-step coverage on linear networks, as well as, multi-layer perceptron for nonlinear prediction and classification explaining all stages of processing and model development illustrated through practical examples and case studies. Later chapters present an extensive coverage on Self Organizing Maps for nonlinear data clustering, recurrent networks for linear nonlinear time series forecasting, and other network types suitable for scientific data analysis.
With an easy to understand format using extensive graphical illustrations and multidisciplinary scientific context, this book fills the gap in the market for neural networks for multi-dimensional scientific data, and relates neural networks to statistics.
Features
§ Explains neural networks in a multi-disciplinary context
§ Uses extensive graphical illustrations to explain complex mathematical concepts for quick and easy understanding
? Examines in-depth neural networks for linear and nonlinear prediction, classification, clustering and forecasting
§ Illustrates all stages of model development and interpretation of results, including data preprocessing, data dimensionality reduction, input selection, model development and validation, model uncertainty assessment, sensitivity analyses on inputs, errors and model parameters
Sandhya Samarasinghe obtained her MSc in Mechanical Engineering from Lumumba University in Russia and an MS and PhD in Engineering from Virginia Tech, USA. Her neural networks research focuses on theoretical understanding and advancements as well as practical implementations.
Zielgruppe
Researchers and graduate students in Engineering and Applied and Life Sciences, system analysts, and modelers.
Autoren/Hrsg.
Fachgebiete
Weitere Infos & Material
FROM DATA TO MODELS: COMPLEXITY AND CHALLENGES IN UNDERSTANDING BIOLOGICAL, ECOLOGICAL, AND NATURAL SYSTEMS
Introduction
Layout of the Book
FUNDAMENTALS OF NEURAL NETWORKS AND MODELS FOR LINEAR DATA ANALYSIS
Introduction and Overview
Neural Networks and Their Capabilities
Inspirations from Biology
Modeling Information Processing in Neurons
Neuron Models and Learning Strategies
Models for Prediction and Classification
Practical Examples of Linear Neuron Models on Real Data
Comparison with Linear Statistical Methods
Summary
Problems
NEURAL NETWORKS FOR NONLINEAR PATTERN RECOGNITION
Overview and Introduction
Nonlinear Neurons
Practical Example of Modeling with Nonlinear Neurons
Comparison with Nonlinear Regression
One-Input Multilayer Nonlinear Networks
Two-Input Multilayer Perceptron Network
Case Studies on Nonlinear Classification and Prediction with Nonlinear Networks
Multidimensional Data Modeling with Nonlinear Multilayer Perceptron Networks
Summary
Problems
LEARNING OF NONLINEAR PATTERNS BY NEURAL NETWORKS
Introduction and Overview
Supervised Training of Networks for Nonlinear Pattern Recognition
Gradient Descent and Error Minimization
Backpropagation Learning and Illustration with an Example and Case Study
Delta-Bar-Delta Learning and Illustration with an Example and Case Study
Steepest Descent Method Presented with an Example
Comparison of First Order Learning Methods
Second-Order Methods of Error Minimization and Weight Optimization
Comparison of First Order and Second Order Learning Methods Illustrated through an Example
Summary
Problems
IMPLEMENTATION OF NEURAL NETWORK MODELS FOR EXTRACTING RELIABLE PATTERNS FROM DATA
Introduction and Overview
Bias-Variance Tradeoff
Illustration of Early Stopping and Regularization
Improving Generalization of Neural Networks
Network structure Optimization and Illustration with Examples
Reducing Structural Complexity of Networks by Pruning
Demonstration of Pruning with Examples
Robustness of a Network to Perturbation of Weights Illustrated Using an Example
Summary
Problems
DATA EXPLORATION, DIMENSIONALITY REDUCTION, AND FEATURE EXTRACTION
Introduction and Overview
Data Visualization Presented on Example Data
Correlation and Covariance between Variables
Normalization of Data
Example Illustrating Correlation, Covariance and Normalization
Selecting Relevant Inputs
Dimensionality Reduction and Feature Extraction
Example Illustrating Input Selection and Feature Extraction
Outlier Detection
Noise
Case Study: Illustrating Input Selection and Dimensionality Reduction for a
Practical Problem
Summary
Problems
ASSESSMENT OF UNCERTAINTY OF NEURAL NETWORK MODELS USING BAYESIAN STATISTICS
Introduction and Overview
Estimating Weight Uncertainty Using Bayesian Statistics
Case study Illustrating Weight Probability Distribution
Assessing Uncertainty of Neural Network Outputs Using Bayesian Statistics
Case Study Illustrating Uncertainty Assessment of Output Errors
Assessing the Sensitivity of Network Outputs to Inputs
Case Study Illustrating Uncertainty Assessment of Network Sensitivity to Inputs
Summary
Problems
DISCOVERING UNKNOWN CLUSTERS IN DATA WITH SELF-ORGANIZING MAPS
Introduction and Overview
Structure of Unsupervised Networks for Clustering Multidimensional Data
Learning in Unsupervised Networks
Implementation of Competitive Learning Illustrated Through Examples
Self-Organizing Feature Maps
Examples and Case Studies Using Self-Organizing Maps on Multi-Dimensional Data
Map Quality and Features Presented through Examples
Illustration of Forming Clusters on the Map and Cluster Characteristics
Map Validation and an Example
Evolving Self-Organizing Maps
Examples Illustrating Various Evolving Self Organizing Maps
Summary
Problems
NEURAL NETWORKS FOR TIME-SERIES FORECASTING
Introduction and Overview
Linear Forecasting of Time-Series with Statistical and Neural Network Models
Example Case Study
Neural Networks for Nonlinear Time-Series Forecasting
Example Case Study
Hybrid Linear (ARIMA) and Nonlinear Neural Network Models
Example Case Study
Automatic Generation of Network Structure Using Simplest Structure Concept-Illustrated Through Practical Application Case Study
Generalized Neuron Network and Illustration Through Practical Application Case
Study
Dynamically Driven Recurrent Networks
Practical Application Case Studies
Bias and Variance in Time-Series Forecasting Illustrated Through an Example
Long-Term Forecasting and a Case study
Input Selection for Time-Series Forecasting
Case study for Input Selection
Summary
Problems
