Book Contents
The book offers
a new theoretical framework for modern statistical inference problems, generally
referred to as learning problems. They arise in connection with hard
operational problems to be solved in the lack of all necessary knowledge.
The success of their solutions lies in a suitable mix of computational
skill in processing the available data and sophisticated attitude in
stating logical relations between their properties and the expected
behavior of candidate solutions. The framework is discussed through
rigorous mathematical statements in the province of probability theory.
But this does not prevent the authors from grounding the presentation in
the immediate intuition of the reader, writing a highly comprehensive
style and coloring it with examples from everyday life.
The first two chapters
describe the theoretical framework, dealing respectively with probability
models and basilar inference tools. The third chapter presents the
computational learning theory. The fourth chapter deals with problems of
linear and nonlinear regression, while the fifth chapter throws a
statistical perspective on the universe of neural networks examining
various approaches, including hybridations with classical AI systems.
Book Authors
Bruno Apolloni received
his degree in Mechanical Engineering from the Universitą degli Studi di
Napoli, Italy, in 1969. He is professor in Computer Science and teaches
Cybernetics and Information Theory at Dipartimento di Scienze dell'
Informazione of University of Milano, Italy. His main research interests
are twofold: in the frontier area between probability and statistics, and
theoretical computer science with special regard to computational
learning, pattern recognition, optimization, control theory, probabilistic
analysis of algorithms, epistemological aspects of probability and
fuzziness. Since 1989 he has been head of the Neural Networks Research
Laboratory (LAREN) of the above department. Since 2001 he is President of
the Italian Society of Neural Networks (SIREN,
http://siren.dsi.unimi.it/). He has authored over a hundred
papers.
Dario Malchiodi received a
degree in Computer Science in 1996 and a Ph.D. degree in Applied
Mathematics in 2000, both from the University of Milano, Italy. He is
currently assistant professor at the same University, where he teaches
Computer Programming and Foundations of Computer Science. His main
research area ranges from probability theory and mathematical statistics
to various aspects of computational learning theory, including
applications of these fields to neural networks, pRAMs and support-vector
machines.
Sabrina Gaito
received a degree in Physics in 1996, a master degree in Material Science
in 1998 and a Ph.D. in Applied Mathematics in 2002 from the University of
Milano, Italy. She is currently assistant professor at the same
university, where she teaches Foundations of Computer Science and
Statistics. Her interests are mainly in computational physics and the
applications of game theory and mathematical statistics in computational
learning theory. |
