No CrossRef data available.
Article contents
What connectionist models learn: Learning and representation in connectionist networks
Published online by Cambridge University Press: 19 May 2011
Abstract
Connectionist models provide a promising alternative to the traditional computational approach that has for several decades dominated cognitive science and artificial intelligence, although the nature of connectionist models and their relation to symbol processing remains controversial. Connectionist models can be characterized by three general computational features: distinct layers of interconnected units, recursive rules for updating the strengths of the connections during learning, and “simple” homogeneous computing elements. Using just these three features one can construct surprisingly elegant and powerful models of memory, perception, motor control, categorization, and reasoning. What makes the connectionist approach unique is not its variety of representational possibilities (including “distributed representations”) or its departure from explicit rule-based models, or even its preoccupation with the brain metaphor. Rather, it is that connectionist models can be used to explore systematically the complex interaction between learning and representation, as we try to demonstrate through the analysis of several large networks.
Keywords
Information
- Type
- Target Article
- Information
- Copyright
- Copyright © Cambridge University Press 1990
References
Ackley, D., Hinton, G. E. & Sejnowski, T. J. (1985) A learning algorithm for Boltzmann machines. Cognitive Science 9(1): 147–69. {aSJH, GDAB}Google Scholar
Albus, J. S. (1975) A new approach to manipulator control: The cerebellar model articulation controller (CMAC). American Society of Engineers, Transactions G (Journal of Dynamic Systems, Measurement and Control) 97(3): 220–27. {aSJH}Google Scholar
Allen, R. B. (1990) Connectionist language users. Bellcore Technical Report. Morristown, NJ. {rSJH}CrossRefGoogle Scholar
Andersen, R. A. (1986) Value, variable, and coarse coding by posterior parietal neuronns. Behavioral and Brain Sciences 9:90–91. {SB}CrossRefGoogle Scholar
Andersen, R. A., Asanuma, C. & Cowan, W. M. (1985) Callosal and prefrontal associational-projecting cell populations in area 7a of the macaque monkey: A study using retrogradely transported fluorescent dyes. Journal of Comparative Neurology 232:443–55. {SB}CrossRefGoogle ScholarPubMed
Andersen, R. A., Essick, G. K. & Siegel, R. M. (1987) Neurons of area 7 activated by both visual stimuli and oculomotor behavior. Experimental Brain Research 67:316–22. {SB}CrossRefGoogle ScholarPubMed
Anderson, J. A., Silverstein, J. W. & Ritz, S. R., Jones, R. S. (1977) Distinctive features, categorical perception, and probability learning: Some applications of a neural model. Psychological Review 84:413–451. {aSJH}CrossRefGoogle Scholar
Anderson, J. R. (1983) The architecture of cognition. Harvard University Press. {aSJH}Google Scholar
Atrim, J. & Bridgeman, B. (1989) The physiology of attention: Participation of cat striate cortex in behavioral choice. Psychological Research 50:223–28. {BB}Google Scholar
Barash, S., Bracewell, R. M., Fogassi, L. & Andersen, R. A. (1989) Interactions of visual and motor-planning activities in the lateral intra-parietal area (LIP). Society for Neuroscience Abstracts 15:1203. {SB}Google Scholar
Barron, A. R., & Barron, R. L. (1988) Statistical learning networks: A unifying view. Symposium on the interface: Statistics and computing science. April 21–23, Reston, VA. {RMG}Google Scholar
Baum, E. B. (1989) A proposal for more powerful learning algorithms. Neural Computation 1(2):201–07. {rSJH}CrossRefGoogle Scholar
Baum, E. B., & Haussler, D. (1988) What size net gives valid generalization? In: Advances in neural information processing systems 1, ed. Touretzky, D.. Morgan-Kaufman. {arSJH}Google Scholar
Baum, E. B., & Wilczek, F. (1987) Supervised learning of probability distributions by neural networks. In: Neural information processing systems, ed. Anderson, D.. American Institute of Physics. {aSJH}Google Scholar
Blum, A. & Rivest, R. (1989) Training a 3-node neural network is NP-complete. In: Advances in neural information processing systems 1, ed. Touretzky, D.. Morgan-Kaufman. {arSJH}Google Scholar
Bower, G. H., & Hilgard, E. R. (1981) Theories of learning, 5th ed.Prentice Hall. {JKK}Google Scholar
Branch, M. N. (1982) Misrepresenting behaviorism. Behavioral and Brain Sciences 5:372–73. {WSM}CrossRefGoogle Scholar
Bridgeman, B. (1980) Temporal response characteristics of cells in monkey striate cortex measured with metacontrast masking and brightness discrimination. Brain Research 196:347–64. {BB}CrossRefGoogle ScholarPubMed
(1982) Multiplexing in single cells of the alert monkey’s visual cortex during brightness discrimination. Neuropsychologia 20:33–42. {BB}Google Scholar
(in press) Review of C. Koch & I. Segev (eds.),Methods in neuronal modeling. Science Books and Films. {BB}Google Scholar
Brown, G. D. A., & Oaksford, M. (1990a) Symbolic behaviour and code generation: The emergence of “equivalence relations” in neural networks. In: Cybernetics and systems ’90, ed. Trappl, R.. World Scientific Publishing Corp. {GDAB}Google Scholar
(1990b) The development of “symbolic behaviour” in natural and artificial neural networks. In: Parallel processing in neural systems and computers, ed. Eckmiller, R., Hartmann, G. & Hauske, G.. Elsevier Science Publishers. {GDAB}Google Scholar
Burr, D. J. (1988) Experiments on neural net recognition of spoken and written text. IEEE Transactions on Acoustics, Speech and Signal Processing 36(7). {aSJH}CrossRefGoogle Scholar
Carroll, S. M., & Dickenson, B. (1989) Construction of neural nets using the radon transform. Proceedings of the International Joint Conference on Neural Networks. {aSJH}CrossRefGoogle Scholar
Chandrasekaran, B., Goel, A. & Allemang, D. (1988) Information processing abstractions: The message still counts more than the medium. Behavioral and Brain Sciences 11:26–27. {KH}CrossRefGoogle Scholar
Chater, N. & Oaksford, M. (1990) Autonomy, implementation and cognitive architecture: A reply to Fodor and Pylyshyn. Cognition 34:93–107. {NC}CrossRefGoogle ScholarPubMed
Chauvin, Y. (1989) A back propagation network with optimal use of hidden units. In: Advances in neural information processing, ed. Touretzky, D., Systems 1. Morgan-Kaufman. {aSJH}Google Scholar
Chomsky, N. (1959) A review of B. F. Skinner’s Verbal behavior. Language 35:26–58. {aSJH}CrossRefGoogle Scholar
Churchland, P. S., & Sejnowski, T. J. (1989) Neural representation and neural computation. In: Neural connections, mental computation, ed. Nadel, L., Cooper, L., Culicover, P. & Harnish, M.. Bradford Books/MIT Press. {NES}Google Scholar
Cooper, P. (1962) The hypersphere in pattern recognition. Information and Control 5:324–46. {aSJH}CrossRefGoogle Scholar
Cover, T. M. (1965) Geometrical and Statistical Properties of linear inequalities with applications to pattern recognition. IEEE Transactions on Electronic Computers, vol. EC-14, 3. {aSJH}CrossRefGoogle Scholar
Crick, F. C. (1989) Neural Edelmanism. Trend in Neuroscience 12:240–48. {GT}CrossRefGoogle ScholarPubMed
Cybenko, G. (in press) Approximation by superposition of a sigmoidal function. Mathematical Control Systems Signals. {aSJH}Google Scholar
Derthick, M. (1987) A connectionist architecture for representing and reasoning about structured knowledge. Research Report No. CMU-BOLTZ-29. Department of Computer Science, Carnegie-Mellon University. {NC}Google Scholar
Dietterich, T. G., & Shavlik, J. W., eds. (in press) Readings in machine learning. Morgan Kaufmann. {PL}Google Scholar
Donahoe, J. W., & Palmer, D. C. (1989) The interpretation of complex human behavior: Some reactions to parallel distributed processing. Journal of the Experimental Analysis of Behavior 51:399–416. {WSM}CrossRefGoogle Scholar
Duda, R. O., & Hart, P. E. (1973) Pattern classification and scene analysis. J. Wiley. {aSJH}Google Scholar
Dugdale, N. & Lowe, C. F. (1990) Naming and stimulus equivalence. In: Behaviour analysis in theory and practice: Contributions and controversies, ed. Blackman, D. E. & Lejeune, H.. Lawrence Erlbaum Associates. {GDAB}Google Scholar
Durbin, R. & Rumelhart, D. E. (1989) Product units: A computationally powerful and biologically plausible extension to backpropagation networks. Neural Computation 1:133–42. {aSJH}CrossRefGoogle Scholar
Edelman, G. (1987) Neural Darwinism: The theory of neuronal group selection. Basic Books. {MW}Google Scholar
Elman, J. (1988) Finding structure in time. Center for Research on Language Technical Report 8801. Center for Research in Language, University of California, San Diego, CA. {arSJH}Google Scholar
(1989) Representation and structure in connectionist models. Technical Report 8903. Center for Research in Language, University of California, San Diego, CA. {MW}Google Scholar
Epstein, R. (1982) Representation: A concept that fills no gaps. Behavioral and Brain Sciences 5:377–78. {WSM}CrossRefGoogle Scholar
Estes, W. K. (1959) Toward a statistical theory of learning. Psychology Review 57:94–107. {rSJH}CrossRefGoogle Scholar
Estes, W. K., Campbell, J. A., Hatsopoulos, N. & Hurwitz, J. B. (1988) Base-rate effects in category learning: A comparison of parallel network and memory storage-retrieval models. Journal of Experimental Psychology, Learning, Memory ir Cognition 15:556–76. {JKK}CrossRefGoogle Scholar
Feldman, J. A. (1985) Connectionist models and their applications. Cognitive Science, Special Issue 9:1. {aSJH}Google Scholar
Feldman, J. A., & Ballard, D. H. (1982) Connectionist models and their properties. Cognitive Science 6:205–54. {JER}CrossRefGoogle Scholar
Fisher, D. H., & McKusick, K. B. (1989) An empirical comparison of ID3 and back-propagation. Proceedings of the Eleventh International Joint Conference on Artificial Intelligence, Detroit, MI. Morgan Kaufmann. {PL}Google Scholar
Fodor, J. & Pylyshym, Z. (1988) Connectionism and cognitive architecture: A critical analysis. In: Connections and symbols, ed. Pinker, S. & Meher, J.. MIT Press. {aSJH, JH, GDAB, NC, PL, TVG}Google Scholar
Francis, W. N., & Kucera, H. (1979) Manual of information to accompany a standard corpus of present-day edited American English for use with digital computers. Department of Linguistics, Brown University. {aSJH}Google Scholar
Fujimura, O. (1987) Fundamentals and applications in speech production research. Proceedings of the XIth Congress on Phonetic Science 6:10–27. {MIJ}Google Scholar
Gibson, J. J. (1966) The senses considered as perceptual systems. Houghton Mifflin. {WAP}Google Scholar
Giles, C, Griffin, R. D. & Maxwell, T. (1988) Encoding geometric in variances in higher order neural networks. In: Neural information processing - natural and synthetic, ed. Anderson, D.. American Institute of Physics. {aSJH}Google Scholar
Gluck, M. A., & Bower, G. H. (1986) Conditioning and categorization: Some common effects of informational variables in animal and human learning. Cognitive science meeting, Amherst, MA. {aSJH}Google Scholar
(1988) A configural-cue network model of classification learning. Presented at the Psychonomic Society Annual Conference, Chicago. {KH}Google Scholar
(1988) Evaluating an adaptive network model of human learning. Journal of Memory and Language 27:166–95. {JKK}CrossRefGoogle Scholar
Gluck, M. A., & Chow, W. (1989) Dynamic stimulus-specific learning rates and the representation of dimensionalized stimulus structures. Paper submitted to the IEEE Conference on Neural Information Processing Systems, November 27–30, Denver, CO. {JKK}Google Scholar
Gold, E. M. (1967) Language identification in the limit. Information and Control 16:447–74. {rSJH}CrossRefGoogle Scholar
Golden, R. (1988a) A unified framework for connectionist systems. Biological Cybernetics 59:109–20. {aSJH, RMG}CrossRefGoogle ScholarPubMed
Gorman, P. R., & Sejnowski, T. (1988) Learned classification of sonar targets using a massively parallel network. IEEE Transactions on Acoustics Speech and Signal Processing 36:1135–40. {aSJH, JER}CrossRefGoogle Scholar
Grossberg, S. (1976) Adaptive pattern classification and universal recoding I. Parallel development and coding of neural feature detectors. Biological Cybernetics 23:121–34. {aSJH}CrossRefGoogle ScholarPubMed
(1987) Competitive learning: From interactive activation to adaptive resonance. Cognitive Science 11(1):23–64. {aSJH, JKK, MW}CrossRefGoogle Scholar
Hancock, P. J. B. (1989) Data representation in neural nets: An empirical study. In: Proceedings of the connectionist models summer school, ed. Touretzky, D., Hinton, G. & Sejnowski, T.. Morgan Kaufmann. {WAP}Google Scholar
Hanson, S. J. (in press) The stochastic delta rule. Physica D. {aSJH}Google Scholar
Hanson, S. J., & Bauer, M. (1986) Conceptual clustering, machine learning and polymorphy. In: Uncertainty in artificial intelligence, ed. Kanal, L. & Lemmer, J.. Amsterdam. {aSJH}Google Scholar
(1989) Conceptual clustering, categorization, and polymorphy. Machine Learning 3:343–72. {aSJH}CrossRefGoogle Scholar
Hanson, S. J., & Burr, D. J. (1987a) Knowledge representation in connectionist networks. Unpublished manuscript. {aSJH}Google Scholar
(1987b) Minkowski-r Backpropagation: Learning in connectionist models with non-Euclidean error signals. In: Proceedings of neural networks: Natural and synthetic, ed. Anderson, D.. American Institute of Physics. {aSJH}Google Scholar
Hanson, S. J., & Kegl, J. (1987) PARSNIP: A connectionist model that learns natural language grammar from exposure to natural language sentences. Ninth Annual Cognitive Science Conference, Seattle, WA. {aSJH, RMG}Google Scholar
Hanson, S. J., & Pratt, L. (1989) Some comparisons of constraints for back-propagation networks. In: Advances in neural information processing, ed. Touretzky, D.. Morgan-Kaufmann. {aSJH}Google Scholar
Hanson, S. J., & Olson, C. R. (1988) A connectionist network that computes limb position in a head-centered coordinate frame. Society for Neuroscience Abstracts, Neurosciences Conference, Toronto, Ontario. {aSJH}Google Scholar
Harnad, S. (in press) The symbol grounding problem. Physica D. {aSJH, JH}Google Scholar
Hebb, D. O. (1949) Organization of behavior: A neuropsychological theory. Wiley. {aSJH, WAP, MW}Google Scholar
Hendler, J. (1989a) Marker-passing over microfeatures: Towards a hybrid symbolic/connectionist model. Cognitive Science 13(1):79–106. {JH}Google Scholar
(1989b) Spreading activation over distributed microfeatures. In: Advances in neural information processing systems 1, ed. Touretzky, D. S.. Morgan-Kaufman. (Collected papers of the IEEE Conference on Neural Information Processing Systems — Natural and Synthetic, Denver 1988.) {JH}Google Scholar
(submitted) Spreading actuation in PDP networks. {JH}Google Scholar
Hinton, G. E. (1981) Implementing semantic networks in parallel hardware. In: Parallel models of associative memory, ed. Hinton, G. E. & Anderson, J. A.. Lawrence Erlbaum Associates. {NC}Google Scholar
(1987a) Learning procedures for connectionist models. Carnegie Mellon University technical report. {aSJH}Google Scholar
(1987b) Learning distributed representations of concepts. In: Eighth Annual Conference of the Cognitive Science Society. Lawrence Erlbaum. {aSJH, NC}Google Scholar
Hinton, G. E., McClelland, J. L. & Rumelhart, D. E. (1986) Distributed representations. In: Parallel distributed processing: Explorations in the microstructure of cognition, vol. 1, ed. McClelland, J. L. & Rumelhart, D. E.. MIT Press. {KH}Google Scholar
Hornik, K., Stinchcombe, M. & White, H. (1988) Multi-layer feedforward networks are universal approximators. Unpublished manuscript. {aSJH}CrossRefGoogle Scholar
Hyvarinen, J. & Poranen, A. (1974) Function of the posterior-associative area 7 as revealed from cellular discharge in alert monkeys. Brain 97:673–92. {SB}CrossRefGoogle Scholar
Iba, W. & Langley, P. (1987) A computational theory of motor learning. Computational Intelligence 3:338–50. {PL}Google Scholar
Jacobs, R. A., Jordan, M. I., & Barto, A. G. (1990) Task decomposition through competition in a modular connectionist architecture: The what and where vision tasks. Cognitive Science {MIJ}CrossRefGoogle Scholar
Jordan, M. I. (1986a) Serial order: A parallel processing approach. Center for Human Information Processing, University of California at San Diego technical report. {aSJH}Google Scholar
(1986b) Attractor dynamics and parallelism in a connectionist sequential machine. In: Proceedings of the 1986 Cognitive Science Conference. Lawrence Erlbaum. {rSJH}Google Scholar
(1990) Motor learning and the degrees of freedom problem. In: Attention and performance XIII, ed. Jeannerod, M.. Erlbaum. {MIJ}Google Scholar
Judd, J. S. (1987) Learning in networks is hard. In: Proceedings of the First International Conference on Neural Networks. IEEE, June, San Diego, CA. {aSJH}Google Scholar
(1988) On the complexity of loading shallow neural networks. Journal of Complexity 4(3): 177–92. {rSJH}CrossRefGoogle Scholar
Kaplan, S., Weaver, M. & French, R. M. (1990) Active symbols and internal models: Towards a cognitive connectionism. AI & Society 4(1). {MW}Google Scholar
Kehoe, E. J. (1988) A layered network model of associative learning: Learning to learn and configuration. Psychological Review 95:411—33. {WSM}CrossRefGoogle ScholarPubMed
(1989) Connectionist models of conditioning: A tutorial. Journal of the Experimental Analysis of Behavior 52:427–40. {WSM}CrossRefGoogle Scholar
Kehoe, E. J., Schreuers, B. G. & Graham, P. (1987) Temporal primacy overrides prior training in serial compound conditioning of the rabbit’s nictitating membran eresponse. Animal Learning & Behavior 15:455–64. {WSM}CrossRefGoogle Scholar
Klahr, D., Langley, P. & Neches, R., eds. (1987) Production system models of learning and development. MIT Press. {PL}CrossRefGoogle Scholar
Koch, C. & Segev, I. (1989) Methods in neuronal modeling. Bradford Books/MIT Press. {BB}Google Scholar
Koford, K. A. (1962) Adaptive network organization. Stanford Electronics Laboratory Quarterly Research Review, No. 3. {aSJH}Google Scholar
Kohonen, T. (1977) Associative memory: A system-theoretical approach. Springer-Verlag. {aSJH}CrossRefGoogle Scholar
Kohler, W. (1925) The mentality of apes (trans, by Winter, E.). Harcourt, Brace & World. {NES}Google Scholar
Krebs, J. (1978) Optimal foraging: Decision rules for predators. In: Behavioral ecology: An evolutionary approach, ed. Krebs, J. R. & Davies, N. B.. Sinauer. {aSJH}Google Scholar
Kruskal, J. & Shepard, R. (1974) A nonmetric variety of linear factor analysis. Psychometrika 39:2. {aSJH}CrossRefGoogle Scholar
Kruschke, J. K. (in progress) A connectionist model of category learning. Ph.D. dissertation, University of California at Berkeley. {JKK}Google Scholar
Laird, J. E., Rosenbloom, P. S. & Newell, A. (1985) Towards chunking as a general learning mechanism. Technical Report CMU-CS-85–110. Department of Computer Science, Carnegie Mellon University {aSJH}Google Scholar
Langley, P. (1983) Representational issues in learning systems. Computer 16(9): 47–51. {aSJH}Google Scholar
Lachter, J. & Bever, T. G. (1988) The relations between linguistic structure and associative theories of language learning: A constructive critique of some connectionist learning models. Cognition 28:195–247. {JKK}CrossRefGoogle ScholarPubMed
Laird, J., Yager, E. S., Tuck, C. M. & Hucka, M. (1989) Learning in teleautonomous systems using SOAR. Proceedings of the 1989 NASA Conference on Space Telerobotics. {PL}Google Scholar
LeCun, Y. (1989) Generalization and network design strategies. In: Connectionism in perspective, ed. Pfeifer, R., Schreter, Z., Fogelman, F. & Steels, L.. Elsevier. {MIJ}Google Scholar
Langley, P. (1983) Representational issues in learning systems. IEEE Computer 16:47–51. {PL}CrossRefGoogle Scholar
(1989) Toward a unified science of machine learning. Machine Learning 3:253–59. {PL}CrossRefGoogle Scholar
Lehky, S. R., & Sejnowski, T. J. (1988) Network model of shape-from-shading: Neural function arises from both receptive and projective fields. Nature 333:452–54. {JKK}CrossRefGoogle ScholarPubMed
Lenat, D. (1985) The role of heuristics in learning by discovery: Three case studies. In: Machine learning, ed. Michalski, R. S., Carbonell, J. G., & Mitchell, T. M.. Tioga Publishing. {aSJH}Google Scholar
Lenat, D. B., & Brown, J. S. (1984) Why AM and EURISKO appear to work. Artificial Intelligence 23:269–94. {KL}CrossRefGoogle Scholar
Levelt, W. J. M. (1974) Forman grammars in linguistics and psycholinguistics, 3 vols. Mouton. {WJML}Google Scholar
Lightfoot, D. (1989) The child’s trigger experience: Degree-0: Learnability. Behavioral and Brain Sciences 12(2): 321–75. {aSJH}CrossRefGoogle Scholar
Logue, A. W. (1982) Cognitive psychology’s representation of behaviorism. Behavioral and Brain Sciences 5:381–82. {WSM}CrossRefGoogle Scholar
Longuet-Higgins, C, Willshaw, D. J. & Buneman, O. P. (1970) Theories of associative recall. Quarterly Review of Biophysics 3(2): 223–44. {aSJH}CrossRefGoogle ScholarPubMed
Luce, D. & Krumhansl, C. (1990) Measurement, scaling and psychophysics. In: Steven’s handbook of experimental psychology, ed. Atkinson, R. C., Lindzay, D., Herrnstein, R. J. & Luce, D.. Wiley Interscience. {aSJH}Google Scholar
Lynch, J. C, Mountcastle, V. B., Talbot, W. H. & Yin, T. C. T. (1977) Parietal lobe mechanisms for directed visual attention. Journal of Neurophysiology 40:362–89. {SB}Google ScholarPubMed
Maki, W. S., & Abunawass, A. (in press) A connectionist approach to conditional discriminations: Learning, short-term, and attention. Presented at the 12th Symposium on Models of Behavior, Harvard University, June 1989. In: Neural network models of conditioning and action, ed. M. Commons, S. Grossberg, & J. Staddon. {WSM}Google Scholar
Massaro, D. W. (1988) Some criticisms of connectionist models of human performance. Journal of Memory and Language 27:213–34. {KH, KL}CrossRefGoogle Scholar
McClelland, J. L. (1986) The programmable blackboard model of reading. In: Parallel distributed processing: Explorations in the microstructure of cognition, vol. 2: Psychological and biological models, ed. McClelland, J. L. & Rumelhart, D. E.. MIT Press. {JER}Google Scholar
McClelland, J. L., & Rumelhart, D. E. (1981) An interactive activation model of context effects in letter perception, Part 1: An account of the basic findings. Psychological Review 88:375–407. {KH, WSM}CrossRefGoogle Scholar
(1985) Distributed memory and the representation of general and specific information. Journal of Experimental Psychology: General 114:159–88. {KH}CrossRefGoogle Scholar
(1986) On learning the past tenses of English verbs. In: Parallel distributed processing, vol. 2, ed. Rumelhart, D. E. & McClelland, J. L.. MIT Press. {JKK}Google Scholar
(1988) Explorations in parallel distributed processing: A handbook of models, programs, and exercises. MIT Press. {KH}Google Scholar
McCloskey, M. & Cohen, N. J. (1987) The sequential learning problem in connectionist modeling. Paper prepared for presentation at the annual meeting of the Psychonomic Society, November, Seattle, WA. {JKK}Google Scholar
McCulloch, W. S., & Pitts, W. (1943) A logical calculus of the ideas imminent in nervous activity. Bulletin of Mathematical Biophysics 5:115–33. {arSJH}CrossRefGoogle Scholar
Mezard, M. & Nadal, J. P. (1989) Learning in feedforward layered networks: The tiling algorithm. Journal of Physiology A: Mathematics General 22:2191–203. {GT}CrossRefGoogle Scholar
Minsky, M. (1961) Steps towards artificial intelligence. Proceedings of the Institute of Radio Engineers 49:8–30. {aSJH}Google Scholar
Minsky, M. & Papert, S. (1969) The perceptron: Principles of computational geometry. MIT Press. {aSJH}Google Scholar
Minton, S. (1988) Quantitative results concerning the utility of explanation-based learning. Proceedings of the Seventh National Conference on Artificial Intelligence, St. Paul, MN. Morgan Kaufmann. {PL}Google Scholar
Miyata, Y. (1988) The learning and planning of actions. Ph.D. thesis, Psychology Department, University of California at San Diego. Technical Report 8802, Institute for Cognitive Science. {rSJH}Google Scholar
Mooney, R., Shavlik, S., Towell, G. & Gove, A. (1989) An experimental comparison of symbolic and connectionist learning algorithms. Proceedings of the Eleventh International Joint Conference on Artificial Intelligence, Detroit, MLMorgan Kaufmann. {PL}Google Scholar
Mozer, M. & Smolensky, P. (1989) Skeletonization: A technique for trimming the fat from a network via relevance assessment. In: Advances in neural information processing systems, ed. Touretzky, D.. Morgan Kaufman. {aSJH}Google Scholar
Murdock, B. B. (1979) Convolution and correlation in perception and memory. In: Perspectives on memory research: Essays in honor of Uppsala University’s 500th anniversary, ed. L.-G. Nilsson. {TVG}Google Scholar
Nadel, L. (1982) Some thoughts on the proper foundations for the study of cognition in animals. Behavioral and Brain Sciences 5:383–84. {WSM}Google Scholar
Natarajan, B. K. (1987) On learning Boolean functions. Proceedings of the Nineteenth Annual Association for Computing Machinery Symposium on Theory of Computing. {rSJH}CrossRefGoogle Scholar
Newell, A. & Simon, H. (1976) Computer science as an empirical inquiry. Communications of the Association for Computing Machinery 19:113—26. {TVG}CrossRefGoogle Scholar
Nilsson, N. J. (1965) Learning machines: Foundations of trainable pattern-classifying systems. McGraw-Hill. {aSJH}Google Scholar
Norman, D. A. (1986) Reflections on cognition and parallel distributed processing. In: Parallel distributed processing: Explorations in the microstructure of cognition, vol. 2, ed. McClelland, J. L. & Rumelhart, D. E.. MIT Press. {KH}Google Scholar
Palm, G. (1982) Neural assemblies: An alternative approach to artificial intelligence. Springer-Verlag. {MW}CrossRefGoogle Scholar
Pearlmutter, B. (1988) Learning state space trajectories in recurrent neural networks, CMU technical report, CMU-CS-88–191. {arSJH}CrossRefGoogle Scholar
Phillips, W. A. (1974) On the distinction between sensory storage and short-term visual memory. Perception and Psychophysics 16:283–90. {WAP}CrossRefGoogle Scholar
(1989) Human cognition and neural computation. In: Neural networks: From models to applications, ed. Personnaz, L. & Dreyfus, G.. I.D.S.E.T. Paris, France. {WAP}Google Scholar
Pineda, F. J. (1987) Generalization of back-propagation to recurrent neural networks. Physical Review Letters 19(59): 2229–32. {rSJH}CrossRefGoogle Scholar
(1988) Generalization of backpropagation to recurrent and high-order networks. In: Proceedings of the IEEE Conference on Neural Information Processing Systems-Natural and Synthetic, ed. Anderson, D.. American Institute. {aSJH}Google Scholar
Pinker, S. & Prince, A. (1988) On language and connectionism: Analysis of a parallel distributed processing model of language acquisition. MIT Technical Report, Cognition 28:73–193. {aSJH, NC, KH, JKK}CrossRefGoogle Scholar
Pollack, J. & Waltz, D. (1982) Natural language processing using spreading activation and lateral inhibition. In: Proceedings of the Fourth Annual Cognitive Science Conference. Ann Arbor, MI. {aSJH}Google Scholar
Pylyshyn, Z. (1973) What the mind’s eye tells the mind’s brain: A critique of mental imagery. Psychological Bulletin 80:1–24. {WAP}CrossRefGoogle Scholar
(1984) Computation and cognition: Toward a foundation for cognitive science. Bradford Books/MIT Press. {aSJH, NC}Google Scholar
Rail, W. (1989) Cable theory for dendritic neurons. In: Methods in neuronal modeling, ed. Koch, C. & Segev, I.. Bradford Books/MIT Press. {BB}Google Scholar
Ratcliff, R. (in press) Connectionist models of recognition memory: Constraints imposed by learning and forgetting functions. Psychology Review 97. {JKK}CrossRefGoogle Scholar
Rescorla, R. A., & Wagner, A. R. (1972) A theory of Pavlovian conditioning: Variations in the effectiveness of reinforcement and nonreinforcement. In: Classical conditioning II: Current theory and research, ed. Black, A. H. & Prokasy, W. F.. Appleton-Century-Crofts. {WSM}Google Scholar
Rivest, R., Haussler, D. & Warmuth, M. K. (1989) Proceedings of second annual workshop on computational learning theory. Morgan-Kaufman. {aSJH}Google Scholar
Robinson, D. L., Goldberg, M. E. & Stanton, G. B. (1978) Parietal association cortex in the primate: Sensory mechanisms and behavioral modulations. Journal of Neurophysiology 41:910–32. {SB}CrossRefGoogle ScholarPubMed
Roiblat, H. L. (1982) The meaning of representation in animal memory. Behavioral and Brain Sciences 5:353–72. {WSM}CrossRefGoogle Scholar
Rosch, E., Simpson, C, & Miller, R. S. (1976) Structural bases of typicality effects. Journal of Experimental Psychology: Human Perception and Performance 2:491–502. {JKK}Google Scholar
Rosenberg, C. R. (1987) Analysis of NETtalk’s internal structure. Ninth Annual Cognitive Science Conference, August, Seattle, WA. {aSJH, RMG}Google Scholar
Rumelhart, D. E., Hinton, G. E. & Williams, E. (1986a) Learning internal representations by error propagation. Nature 323:533–36. {aSJH}CrossRefGoogle Scholar
(1986b) Learning representations by back-propagating errors. Nature 323:533–36. {JKK}CrossRefGoogle Scholar
Rumelhart, D. E., & McClelland, J. L. (1986a) Parallel distributed processing: Explorations in tee microstructure of cognition, vol. 1: Foundations. Bradford Books/MIT Press. {aSJH}CrossRefGoogle Scholar
(1986b) On learning the past tenses of English verbs. In: Parallel distributed processing: Explorations in the microstructure of cognition, vol. 1, ed. McClelland, J. L. & Rumelhart, D. E.. MIT Press. {KH}Google Scholar
(1986c) PDF models and general issues in cognitive science. In: Parallel distributed processing, vol. 1, ed. Rumelhart, D. E. & McClelland, J. L.. MIT Press. {JKK, WSM}CrossRefGoogle Scholar
Rumelhart, D. E., Smolensky, P., McClelland, J. L. & Hinton, G. E. (1986) Schemata and sequential thought processes in PDP models. In: Parallel distributed processing: Explorations in the microstructures of cognition, vol. 2: Psychological and biological processes, ed. McClelland, J. L. & Rumelhart, D. E.. MIT Press. {NC}CrossRefGoogle Scholar
Schlimmer, J. C. (1987) Incremental adjustment of representations for learning. Proceedings of the Fourth International Workshop on Machine Learning, Irvine, CA. Morgan Kaufmann. {PL}Google Scholar
Schneider, W. & Detweiler, M. (1987) A connectionist control architecture for working memory. In: The psychology of learning and motivation, vol. 21, ed. Bower, G. H.. Academic Press. {KH}Google Scholar
Searle, J. (1980) Minds, brains, and programs. Behavioral and Brain Sciences 3:417–57. {WAP}CrossRefGoogle Scholar
I., Segev., Fleshman, J. W. & Burke, R. E. (1989) Compartmental models of complex neurons. In: Methods in neuronal modeling, ed. Koch, C. & Segev, I.. Bradford Books/MIT Press. {BB}Google Scholar
Seidenberg, M. S. & McClelland, J. L. (1989) A distributed, developmental model of word recognition and naming. Psychological Review 96:523—68. {KH}.CrossRefGoogle ScholarPubMed
Sejeowski, T. & Rosenberg, C. (1986) NET talk: A parallel network that learns to read aloud. The Johns Hopkins University EE and CS Technical Report, January. {aSJH}Google Scholar
(1986) NETtalk: A parallel network that learns to read aloud. Technical Report JHU/EECS-86/01, Department of Electrical Engineering and Computer Science, Johns Hopkins University. {KH}Google Scholar
Shastri, L. (1985) Evidential reasoning in semantic networks: A formal theory and its parallel implementation. Technical Report 166, September. Department of Computer Science, University of Rochester. {NC}Google Scholar
Shepard, R. N. (1962) The analysis of proximities: Multidimensional scaling with an unknown distance function II. Psychometrika 27:219–46. {aSJH}CrossRefGoogle Scholar
(1987) Toward a universal law of generalization for psychological science. Science 237:1317–23. {aSJH}CrossRefGoogle Scholar
(1988) How fully should connectionism be activated? Two sources of excitation and one of inhibition. Behavioral and Brain Sciences 11:52. {KH}CrossRefGoogle Scholar
(1989) Internal representation of universal regularities: A challenge for connectionism. In: Neural connections and mental computation, ed. Nadel, L., Cooper, L. A., Culicover, P., & Harnish, R. M.. MIT Press/Bradford Books. {aSJH}Google Scholar
Shepard, R. N., Hovland, C. L. & Jenkins, H. M. (1961) Learning and memorization of classifications. Psychological Monographs 75(13):517. {JKK}CrossRefGoogle Scholar
Shepard, R. N., Romney, A. K. & Nerlove, S. B. (1972) Multidimensional scaling. Seminar Press. {aSJH}Google Scholar
Shepherd, G. M., & Brayton, R. K. (1987) Logic operations are properties of computer-simulated interactions between excitable dendritic spines. Neuroscience 21:151–66. {aSJH}CrossRefGoogle ScholarPubMed
Sherrington, D. (ed.) (1989) Special issue in memory of Elizabeth Gardner. Journal of Physiology A: Mathematics General 22. {GGT}Google Scholar
Shvaytser, H. (1989) On exact learning from a finite number of positive examples. Unpublished manuscript. {rSJH}Google Scholar
Singhal, S. (1988) The completely connected network. Bellcore Technical Report. {aSJH}Google Scholar
Sidman, M. & Tailby, W. (1982) Conditional discrimination vs. matching to sample: An expansion of the testing paradigm. Journal of the Experimental Analysis of Behaviour 37:5–22. {GDAB}CrossRefGoogle ScholarPubMed
Smolensky, P. (1987) On variable binding and the representation of symbolic structures in connectionist systems. Technical Report CU-CS-355–87, Department of Computer Science and Institute for Cognitive Science, University of Colorado, Boulder. {NC}Google Scholar
(1988) On the proper treatment of connectionism. Behavioral and Brain Sciences 11(1): 1–59. {arSJH, KH}CrossRefGoogle Scholar
Specht, D. F. (1967) Generation of polynomial discriminant functions for pattern recognition. IEEE Transactions Electronic Computers, EC-16(3):308–19. {aSJH}Google Scholar
Stork, D. G. (1989) Is back propagation biologically plausible? In: International Joint Conference on Neural Networks IEEE, vol. II. {JKK}Google Scholar
Strong, G. W., & Whitehead, B. A. (1989) A solution to the tag-assignment problem for neural networks. Behavioral and Brain Sciences 12:381–97. {JER}CrossRefGoogle Scholar
Sutton, R. S., & Barto, A. G. (1981) Toward a modern theory of adaptive networks: Expectation and prediction. Psychological Review 99:135–70. {WSM}CrossRefGoogle Scholar
Tomko, G. J., & Crapper, D. R. (1974) Neural variability: Non-stationary response to identical visual stimuli. Brain Research 79:405–18. {aSJH}CrossRefGoogle Scholar
Touretzky, D. S., & Hinton, G. E. (1985) Symbols among the neurons: Details of a connectionist inference architecture. In: Proceedings of the Ninth International Joint Conference on Artificial Intelligence, University of California at Los Angeles. {NC}Google Scholar
Touretzky, D. S., & Wheeler, D. (1989) A computational basis for phonology. IEEE Conference on Neural Information Processing Systems. {JER}CrossRefGoogle Scholar
Tversky, A. (1977) Features of similarity. Psychological Review 84:327—52. {aSJH, JKK}CrossRefGoogle Scholar
Valiant, L. G. (1984) A theory of the learnable. Communications of Association for Computing Machinery 27(11): 1134–42. {rSJH}CrossRefGoogle Scholar
(1985) Learning disjunctions of conjunctions. Proceedings of the Ninth International Joint Conference on Artificial Intelligence 560–566, August 18–23, Los Angeles, CA. {aSJH}Google Scholar
Van Gelder, T. J. (1990) Compositionality: A connectionist variation on a classical theme. Cognitive Science 14(2). {TVG}CrossRefGoogle Scholar
(1990) What is the “D” in PDP? A survey of the concept of distribution. In: Philosophy and connectionist theory, ed. Stich, S., Ramsey, W. & Rumelhart, D. E.. Lawrence Erlbaum. {TVG}Google Scholar
Von der Malsburg, C. (1988) Pattern recognition by labeled graph matching. Neural Networks 1:141–48. {WAP}Google Scholar
Werbos, P. J. (1974) Beyond regression: New tools for prediction and analysis in the behavioral sciences. Ph.D. dissertation thesis, Harvard University. {aSJH}Google Scholar
White, H. (1989) Learning in artificial neural networks: A statistical perspective. Discussion paper 89–49. Economics Department, University of California at San Diego. Submitted for publication. {RMG}Google Scholar
Widrow, B. & Hoff, M. E. (1960) Adaptive switching circuits 1960 WESCON Convention Record, Part IV, 96–104. {aSJH}Google Scholar
Wieland, A. & Leighton, R. (1987) Geometric analysis of neural network capabilities. Neural Networks Conference, San Diego, CA {aSJH}Google Scholar
Williams, R. J. (1986) The logic of activation functions. In: Parallel distributed processing: Explorations in the microstructure of cognition, vol. 1: Foundations, ed. Rumelhart, D. E., & McClelland, J. L.. Bradford Books/MIT Press. {aSJH}Google Scholar
Williams, R. J., & Zipser, D. (1988) A learning algorithm for continually running fully recurrent neural networks. Technical Report ICS Report 8805, University of California at San Diego. {aSJH}Google Scholar
(1989) A learning algorithm for continually running fully recurrent neural networks. Neural Computation 1:270–80. {rSJH}CrossRefGoogle Scholar
Wilson, M. A., & Bower, J. M. (1989) The simulation of large-scale neural networks. In: Methods in neuronal modeling, ed. Koch, C. & Segev, I.. Bradford Books/MIT Press. {BB}Google Scholar
Winder, R. O. (1962) Threshold logic. Ph.D. dissertation. Princeton University. {aSJH}Google Scholar
Yin, T. C. T., & Mountcastle, V. B. (1977) Visual input to the visuomotor mechanisms of the monkey’s parietal lobe. Science 197:1381–83. {SB}CrossRefGoogle Scholar
Zentall, T. P., Jagielo, J. A., Jackson-Smith, O. & Urcuioli, P. (1987) Memory codes in pigeon short-term memory: Effects of varying the number of sample and comparison stimuli. Learning and Motivation 18:21—33. {WSM}CrossRefGoogle Scholar
- 134
- Cited by