Abstract
Since ancient time learning has played a significant role in building the basis of human intelligence. The tendency for learning with the increased dynamics and complexity of the global economy is growing. If in the past most of the learning efforts were concentrated in high-school and college years, in the 21st century learning becomes a continuous process during the whole working career. Applied computational intelligence can play a significant role in enhancing the learning capabilities of humans through its unique abilities to discover new patterns and dependencies.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Multilayer perceptrons and support vector machines will be described in detail in subsequent sections.
- 2.
A good survey of all machine learning methods is the book by T. Mitchell, Machine Learning , McGraw-Hill, 1997.
- 3.
W. McCulloch and W. Pitts, A logical calculus of ideas immanent in nervous activity, Bulletin of Mathematical BioPhysics, 5, p. 115, 1943.
- 4.
S. Haykin, Neural Networks: A Comprehensive Foundation, 2nd edition, Prentice Hall, 1999.
- 5.
http://www.learnartificialneuralnetworks.com
- 6.
P. Werbos, Beyond Regression : New Tools for Prediction and Analysis in the Behavioral Sciences, Ph.D. Thesis, Harvard University, Cambridge, MA, 1974.
- 7.
For detailed description, see S. Haykin, Neural Networks: A Comprehensive Foundation, 2nd edition, Prentice Hall, 1999.
- 8.
V. Vapnik, Statistical Learning Theory, Wiley, 1998.
- 9.
A. Koestler, The Ghost in the Machine, Arkana, London, 1989.
- 10.
Curious readers may look for details in the book of V. Vapnik, The Nature of Statistical Learning Theory, 2nd edition, Springer, 2000.
- 11.
V. Cherkassky and F. Mulier, Learning from Data : Concepts, Theory, and Methods, 2nd edition, Wiley, 2007.
- 12.
See details in G. Smits and E. Jordaan, Using mixtures of polynomial and RBF kernels for support vector regression, Proceedings of WCCI 2002, Honolulu, HI, IEEE Press, pp. 2785–2790, 2002.
- 13.
A survey with a good explanation of neural network learning methods can be found in the book: M. Negnevitsky, Artificial Intelligence: A Guide to Intelligent Systems, Addison-Wesley, 2002.
- 14.
http://www.sas.com/success/williamssonoma_em.html
- 15.
http://www.pavtech.com
- 16.
http://www.healthdiscoverycorp.com/products.php
Suggested Reading
A good survey of all machine learning methods is the book by T. Mitchell, Machine Learning , McGraw-Hill, 1997.
The undisputed bible of neural networks is the book:
S. Haykin, Neural Networks: A Comprehensive Foundation, 2nd edition, Prentice Hall, 1999.
A survey with a good explanation of neural network learning methods can be found in the book:
M. Negnevitsky, Artificial Intelligence: A Guide to Intelligent Systems, Addison-Wesley, 2002.
The undisputed bible of statistical learning theory is the book (requires mathematical background):
V. Vapnik, Statistical Learning Theory, Wiley, 1998.
One of the best sources for statistical learning theory and SVM is the book:
V. Cherkassky and F. Mulier, Learning from Data: Concepts, Theory, and Methods, 2nd edition, Wiley, 2007.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Kordon, A.K. (2010). Machine Learning: The Ghost in the Learning Machine. In: Applying Computational Intelligence. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69913-2_4
Download citation
DOI: https://doi.org/10.1007/978-3-540-69913-2_4
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-69910-1
Online ISBN: 978-3-540-69913-2
eBook Packages: EngineeringEngineering (R0)