Machine Learning: A Historical and Methodological Analysis

Machine learning has always been an integral part of artificial intelligcncc, and it.s methodology has evolved in concert, with the major concerns of the field In response to the dificulties of encoding evcrincreasing vohlmes of knowledge in modeln hI syst.ems, many rcsearchers have recently turned their attention to machiuc learning as a means to overcome the knowledge acquisition bottleneck This article pl esents a taxonomic analysis of machine learning organized primarily hy learning strategies and secondarily by knowledge represent,atiou and application areas A historical survey out lining the development of various approaches to machine learning is prcscnted from early neural networks t.o present, knowledge-irltellsive techniques. 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& (ONR) under grant number NO0014-79-C-0661, and in par1 by the National Science Foundation grant MCSB’L-05166 LEARNING rs ,4 MANY-FACETED PIIEN~MEN~N. Learning processes include the accIuisition of new tlcclarative knowlcdgc, t,he development of motor and cognitive skills through instruction or practice, the organization of new knowledge into general, cffcctivc rcprcsontations, and the discovery of new facts and theories through observation and experimentation. The st,udy and computer modclling of learning processes in their multiple manifestations constitutes the subject matter of machine learning Although machine learning has been a central concern in artificial intelligence since t,he early days wlieri the idea of “self-organizing systems” was popular, t,lie limitations inherent in the early neural network approaches led to :I temporary decline in research volume. 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: l Task-Oriented Studies the drvclopmcnt and analysis of lrarning syst,ems oriented toward solving a AI Magazine Volume 4 Number 3 (1983) (© AAAI)