Introduction to Machine Learning

Author : Nils J. Nilsson, Artificial Intelligence Laboratory, Department of Computer Science, Stanford University
Working Draft : September 1996

This book surveys many of the important topics in machine learning circa 1996. The intention was to pursue a middle ground between theory and practice. This book concentrates on the important ideas in machine learning — it is neither a handbook of practice nor a compendium of theoretical proofs. The goal was to give the reader sufficient preparation to make the extensive literature on machine learning accessible.

Machine learning usually refers to the changes in systems that perform tasks associated with artificial intelligence (AI). Such tasks involve recognition, diagnosis, planning, robot control, prediction, etc. The “changes” might he either enhancements to already performing systems or ab initio synthesis of new systems. Different learning mechanisms might be employed depending on which subsystem is being changed. Readers can study several different learning methods in this book.

This book has taken that the thing to be learned is a computational structure of some sort. It considers a variety of different computational structures:

– Functions
– Logic programs and rule sets
– Finite-state machines
– Grammars
– Problem solving systems

This book presents methods both for the synthesis of these structures from examples and for changing existing structures. In the latter case, the change to the existing structure might be simply to make it more computationally efficient rather than to increase the coverage of the situations it can handle.