Machine Learning: From Theory to Applications

This volume includes some of the key research papers in the
area of machine learning produced at MIT and Siemens during
a three-year joint research      effort. It includes papers on
many different styles of machine learning,      organized into
three parts.
Part I, theory, includes three papers on      theoretical aspects
of machine learning. The first two use the theory         of
computational complexity to derive some fundamental limits
on what isefficiently learnable. The third provides an
efficient algorithm for            identifying finite automata.
Part II, artificial intelligence and symbolic   learning
methods, includes five papers giving an overview of the
state   of the art and future developments in the field of
machine learning, a         subfield of artificial intelligence
dealing with automated knowledge            acquisition and knowledge
revision.
Part III, neural and collective      computation, includes five
papers sampling the theoretical diversity and      trends in the
vigorous new research field of neural networks:                     massively
parallel symbolic induction, task decomposition                           through
competition, phoneme discrimination, behavior-based
learning,   and self-repairing neural networks.