Techniques and Methodology

Machine Learning has bcrn a constant, theme t,hroughout AI's two decades of existence In this ovcrview t,hc authors analyze various aspects including the major met,hodological approaches advocated in Machine Learning research, Machine learning has always been an integral part of artificial intelligcncc, and it.s This paper is a modified and extended version of the first chapt.er of Machine Learnznq, An Artijicrul Intelligence Approach, with per mission of the publisher: Tioga Press (Palo Alto, Ch) The research described here was sponsored in palt, by the Office of Naval & scar& More recently, new symbolic met,hods and knowledge-intcnsivc techniques have yielded promising results and these in t.urn have led to the current, revival in machine lcwrning research This article examines some basic methodological issues, proposes a classification of machine learning techniques, and provides a historical review of t,he major research directions The Objectives of Machine Learning The field of machine learning can bc organized around three primary research foci: At, present, itisi ructing a cotnJnit,er or a computer-controlled robot, to perform a t,ask requires one t,o define a comple1.e and correct, algoril,hm for that. Prcsrnt-day computer systeitis cannot truly learn to J)erform a La& through exa1nJ)lcs or by analogy Lo a similar, J)rcviously-solved t,ask. Nor can they improve significantly on t,lle basis of)asl, tnistakes, or acquire new abilities l)y observing and itnit,ating exJ)erts Macllinc learning research strives to open IShe possibility of instructing computers in such new ways, and t.liereby promises Lo ease lhe burden of hand-progratnmirlg growing volutttes of increasingly coniplcx informat ioti into lhe computers of t.omorrow. The t,raditiotlal argumenl that an cnginecring approacll need not reflect human or biological J)erformanc:c is not, truly applicable t,o tuachine learning.