INTRODUCTION MACHINE LEARNING - Stanford AI Lab

← 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.

Learning, like intelligence, covers such a broad range of processes that it is dif- cult to de ne precisely. A dictionary de nition includes phrases such as \to gain knowledge, or understanding of, or skill in, by study, instruction, or expe-rience," and \modi cation of a behavioral tendency by experience." Zoologists

  Learning