Review of "Learning Kernel Classifiers: Theory and Algorithms by Ralf Herbrich." MIT Press, Cambridge, Mass., 2002. ISBN 026208306X, 384 pages; and Review of "Learning with Kernels: Support Vector Machines, Regularization Optimization and Beyond by Bernhard Scholkopf and Alexander J. Smola." IT Press, Cambridge, Mass., 2002, ISBN 0262194759, 644 pages.

ABSTRACT

Pattern recognition is arguably the critical first step in intelligence - be it natural or artificial. Science could not exist if humans were not able to spot regularities. Only subsequently do we analyze and classify them, and ultimately come up with underlying descriptions, some of which eventually make it to the lofty status of natural laws. Of course evolution did NOT ENDOw humans (or animals for that matter) with the ability to recognize patterns so we could build grandiose scientific edifices, rather we need that ability at the most elementary level. Humans simply cannot function in everyday life without pattern recognition capabilities and when those capabilities are impaired, as in patients with Alzheimer's disease for example, the result is nothing less than tragic.

REFERENCES

• 1: Thomas M. Mitchell, Machine Learning, McGraw-Hill Higher Education, 1997
• 2: R. O. Duda, and P. E. Hart, Pattern Classification and Scene Analysis, Wiley, New York, 1973.
• 3: Richard O. Duda , Peter E. Hart , David G. Stork, Pattern Classification (2nd Edition), Wiley-Interscience, 2000
• 4: Vladimir N. Vapnik, The nature of statistical learning theory, Springer-Verlag New York, Inc., New York, NY, 1995
• 5: Nello Cristianini , John Shawe-Taylor, An introduction to support Vector Machines: and other kernel-based learning methods, Cambridge University Press, New York, NY, 1999
• 6: T. Hastie, R. Tibshirani, and J. H. Friedman. The Elements of Statistical Learning. Springer Verlag, Berlin, 2001.
• 7: Vojislav Kecman, Learning and Soft Computing: Support Vector Machines, Neural Networks, and Fuzzy Logic Models, MIT Press, Cambridge, MA, 2001