Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Review Help
Search
The fundamentals of computational intelligence : system approach
Zgurovsky M., Zaychenko Y., Springer International Publishing, New York, NY, 2016. 373 pp. Type: Book (978-3-319351-60-5)
Date Reviewed: Apr 21 2017

Not for the faint-hearted or those without mathematical knowledge, the rhythm of this book is as follows: first, it provides a profound formal description grounded in mathematics in some sections of chapters, and then there is a section that is dedicated to exhibiting some examples or case studies for application. The book can be considered as a handbook for researchers or developers of fundamental algorithms and software, for those who have strong computer science backgrounds.

The first chapter describes basic artificial neural networks (ANN) in mathematical terms. The concluding section analyzes how to set the parameters of radial basis functions to achieve a reasonable approximation.

The second chapter discusses Hopfield, Hamming, and Kohonen networks including self-organizing maps (SOM). The closing chapter deals with the application of Kohonen networks for automatic classification and multidimensional vectors of features.

Chapter 3 analyzes fuzzy inference systems and neural networks. Understanding the chapter requires a good command of fuzzy theory and the related algorithms. The final section summarizes the experimental results of fuzzy networks through tables and figures.

Chapter 4 is dedicated to fuzzy logic systems and applications of fuzzy neural networks in the field of macroeconomics and finance. The sections of the chapter contain numerous comparative studies on the application of various fuzzy networks on different economic parameters. In business sciences and economics, a fashionable research area is the investigation of bankruptcy risks to companies. One of the approaches is the use of fuzzy networks for prediction. The chapter ends with a summary of experiments.

Chapter 5 considers the role of fuzzy neural networks in classification problems. One of the application areas is object recognition in images that are created by various sensors. In hand-written text, mathematical expressions can be recognized using fuzzy networks. The concluding sections describe the relevant results of the experiments in image and object recognition.

Chapter 6 is allocated to the inductive modeling method, group method of data handling (GMDH), which could be used in data mining and data analysis. The fuzzy versions are analyzed as well, and a comparative study is carried out on GMDH and FGMDH (fuzzy version); the results are represented in line diagrams. The intellectual data analysis is composed of data mining, data science tools, and models for forecasting and exploring unknown interrelationships between certain parameters; GMDH analysis can be used for intellectual data analysis.

Chapter 7 is devoted to cluster analysis in intellectual data analysis. The chapter discusses the various clustering methods in mathematical detail, along with several experiments.

The eighth chapter provides an overview of genetic algorithms and evolutionary programming. There are case studies and an assessment of the empirical results. One of the case studies deals with IT communication networks including multiprotocol label switching (MPLS) and its structural synthesis.

Chapter 9 is devoted to portfolio optimization of securities and other financial instruments. The chapter presents a combination of methods and algorithms based on fuzzy theories. The capability of the methods is demonstrated through experimental results and empirical analysis.

The book describes the mathematical equations, inequalities, and functions that can be used to calculate some results and achieve some data analysis objectives. The majority of the proposed and described algorithms are not implemented in some off-the-shelf product, so anybody who would like to use it should hand-code the algorithms. This statement is true even for checking the validity of the presented results.

The book is interesting for researchers working on economic, financial, and societal phenomena, but it requires a deep understanding the underlying mathematical techniques. The book may be useful for researchers of computational intelligence because it contains a comprehensive set of algorithms and their mathematical descriptions.

Reviewer:  Bálint Molnár Review #: CR145209 (1707-0428)
Bookmark and Share
  Reviewer Selected
Featured Reviewer
 
 
Uncertainty, “Fuzzy,” And Probabilistic Reasoning (I.2.3 ... )
 
 
Connectionism And Neural Nets (I.2.6 ... )
 
 
Neural Nets (I.5.1 ... )
 
 
Learning (I.2.6 )
 
 
Models (I.5.1 )
 
Would you recommend this review?
yes
no
Other reviews under "Uncertainty, “Fuzzy,” And Probabilistic Reasoning": Date
Bayesian and non-Bayesian evidential updating
Henry E. J. Artificial Intelligence 31(3): 271-293, 1987. Type: Article
Sep 1 1988
Probabilistic inference by linear optimization
Blake A., John Wiley & Sons, Inc., New York, NY, 1986. Type: Book (9780471911753)
Aug 1 1988
Probabilistic reasoning in intelligent systems: networks of plausible inference
Pearl J., Morgan Kaufmann Publishers Inc., San Francisco, CA, 1988. Type: Book (9780934613736)
Jun 1 1989
more...

E-Mail This Printer-Friendly
Send Your Comments
Contact Us
Reproduction in whole or in part without permission is prohibited.   Copyright 1999-2024 ThinkLoud®
Terms of Use
| Privacy Policy