Previous Topic Back Forward Next Topic
Print Page Frank Dieterle
 
Ph. D. ThesisPh. D. Thesis 2. Theory – Fundamentals of the Multivariate Data Analysis 2. Theory – Fundamentals of the Multivariate Data Analysis 2.7. Neural Networks – Universal Calibration Tools2.7. Neural Networks – Universal Calibration Tools
Home
News
About Me
Ph. D. Thesis
  Abstract
  Table of Contents
  1. Introduction
  2. Theory – Fundamentals of the Multivariate Data Analysis
    2.1. Overview of the Multivariate Quantitative Data Analysis
    2.2. Experimental Design
    2.3. Data Preprocessing
    2.4. Data Splitting and Validation
    2.5. Calibration of Linear Relationships
    2.6. Calibration of Nonlinear Relationships
    2.7. Neural Networks – Universal Calibration Tools
      2.7.1. Principles of Neural Networks
      2.7.2. Topology of Neural Networks
      2.7.3. Training of Neural Networks
    2.8. Too Much Information Deteriorates Calibration
    2.9. Measures of Error and Validation
  3. Theory – Quantification of the Refrigerants R22 and R134a: Part I
  4. Experiments, Setups and Data Sets
  5. Results – Kinetic Measurements
  6. Results – Multivariate Calibrations
  7. Results – Genetic Algorithm Framework
  8. Results – Growing Neural Network Framework
  9. Results – All Data Sets
  10. Results – Various Aspects of the Frameworks and Measurements
  11. Summary and Outlook
  12. References
  13. Acknowledgements
Publications
Research Tutorials
Downloads and Links
Contact
Search
Site Map
Print this Page Print this Page

2.7.   Neural Networks – Universal Calibration Tools

During the last decade, artificial neural networks have gained an increasing popularity in several fields of chemistry [46]-[49], whereby the variety of applications in chemistry is best illustrated in a book written by Zupan and Gasteiger [50]. In the field of multivariate calibration, the class of the multilayer feedforward backpropagation networks is most popular as they allow calibrating relationships, which are linear and nonlinear, and as no assumption of a specific type of model is needed [51]-[55]. In this section, the basics of the multilayer feedforward backpropagation neural networks are briefly explained and then the issues, which are of interest for this study, are introduced. A very detailed discussion of neural networks in multivariate calibration can be found in an excellent tutorial by Despagne and Massart [8]. More information about the mathematical background and about other neural network topologies can be found in textbooks [56]-[58].

Page 43 © Frank Dieterle, 03.03.2019 Navigation