INTRODUCTION MACHINE LEARNING

← Back to document page

INTRODUCTIONTOMACHINE LEARNINGAN EARLY DRAFT OF A PROPOSEDTEXTBOOKNils J. NilssonRobotics LaboratoryDepartment of Computer ScienceStanford UniversityStanford, CA 94305e-mail: 3, 1998Copyrightc 2005 Nils J. NilssonThis material may not be copied, reproduced, or distributed without thewritten permission of the copyright INTRODUCTION . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . is MACHINE LEARNING ? . . . . . . . . . . . . . . . . . of MACHINE LEARNING . . . . . . . . . . . . . . of MACHINE LEARNING . . . . . . . . . . . . . . . . LEARNING Input-Output Functions . . . . . . . . . . . . . . . . . . of LEARNING . . . . . . . . . . . . . . . . . . . . . . Vectors.

the book is not a handbook of machine learning practice. Instead, my goal is ... whenever it changes its structure, program, or data (based on its inputs or in response to external information) in such a manner that its expected future performance improves. Some of these changes, such as the addition of a record

  Change, Book