caa a22 4500 467947546 CHVBK 20180323165701.0 cr unu---uuuuu 170328e19881001xx s 000 0 eng 10.1007/BF00113897 doi (NATIONALLICENCE)springer-10.1007/BF00113897 (NATIONALLICENCE)springer-10.1023/A:1022662305071 Learning and programming in classifier systems [Elektronische Daten] [Richard Belew, Stephanie Forrest] Both symbolic and subsymbolic models contribute important insights to our understanding of intelligent systems. Classifier systems are low-level learning systems that are also capable of supporting representations at the symbolic level. In this paper, we explore in detail the issues surrounding the integration of programmed and learned knowledge in classifier-system representations, including comprehensibility, ease of expression, explanation, predictability, robustness, redundancy, stability, and the use of analogical representations. We also examine how these issues speak to the debate between symbolic and subsymbolic paradigms. We discuss several dimensions for examining the tradeoffs between programmed and learned representations, and we propose an optimization model for constructing hybrid systems that combine positive aspects of each paradigm. Kluwer Academic Publishers, 1988 Subsymbolic nationallicence representation nationallicence inheritance nationallicence tagging nationallicence default hierarchy nationallicence connectionism nationallicence Subsymbolic representation nationallicence Belew Richard Computer Science and Engineering Department, University of California, San Diego (C-014), 92093, La Jolla, CA, U.S.A. aut Forrest Stephanie Teknowledge, Inc., 1850 Embarcadero Road, 94303, Palo Alto, CA, U.S.A. aut Machine Learning Kluwer Academic Publishers 3/2-3(1988-10-01), 193-223 0885-6125 3:2-3<193 1988 3 10994 https://doi.org/10.1007/BF00113897 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/BF00113897 text/html Onlinezugriff via DOI NATIONALLICENCE 773 0- Machine Learning Kluwer Academic Publishers 3/2-3(1988-10-01), 193-223 0885-6125 3:2-3<193 1988 3 10994 NATIONALLICENCE 700 1- Belew Richard Computer Science and Engineering Department, University of California, San Diego (C-014), 92093, La Jolla, CA, U.S.A aut NATIONALLICENCE 700 1- Forrest Stephanie Teknowledge, Inc., 1850 Embarcadero Road, 94303, Palo Alto, CA, U.S.A aut NATIONALLICENCE 856 40 https://doi.org/10.1023/A:1022662305071 text/html Onlinezugriff via DOI NATIONALLICENCE 773 0- Machine Learning Kluwer Academic Publishers-Plenum Publishers 3/2-3(1988-10-01), 193-223 0885-6125 3:2-3<193 1988 3 10994 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer NATIONALLICENCE NATIONALLICENCE NL-springer