creators_name: coward, l andrew type: journalp datestamp: 2002-06-29 lastmod: 2011-03-11 08:54:56 metadata_visibility: show title: The Recommendation Architecture: Lessons from Large-Scale Electronic Systems Applied to Cognition ispublished: pub subjects: behav-neuro-sci subjects: cog-psy subjects: physio-psy full_text_status: public keywords: Cognitive architectures; Computational models; Information context; Functional modules abstract: A fundamental approach of cognitive science is to understand cognitive systems by separating them into modules. Theoretical reasons are described which force any system which learns to perform a complex combination of real time functions into a modular architecture. Constraints on the way modules divide up functionality are also described. The architecture of such systems, including biological systems, is constrained into a form called the recommendation architecture, with a primary separation between clustering and competition. Clustering is a modular hierarchy which manages the interactions between functions on the basis of detection of functionally ambiguous repetition. Change to previously detected repetitions is limited in order to maintain a meaningful, although partially ambiguous context for all modules which make use of the previously defined repetitions. Competition interprets the repetition conditions detected by clustering as a range of alternative behavioural recommendations, and uses consequence feedback to learn to select the most appropriate recommendation. The requirements imposed by functional complexity result in very specific structures and processes which resemble those of brains. The design of an implemented electronic version of the recommendation architecture is described, and it is demonstrated that the system can heuristically define its own functionality, and learn without disrupting earlier learning. The recommendation architecture is compared with a range of alternative cognitive architectural proposals, and the conclusion reached that it has substantial potential both for understanding brains and for designing systems to perform cognitive functions. date: 2001-12 date_type: published publication: Cognitive Systems Research volume: 2 number: 2 publisher: Elsevier pagerange: 115-156 refereed: TRUE referencetext: [1]Anderson, J.A. and Sutton, J.P. (1997). If we compute faster, do we understand better? Behavior Research Methods, Instruments & Computers Methods, Instruments & Computers 29 (1), pages 67-77, 1997 [2]Anderson, J.R. and Lebiere, C. (1998). The Atomic Components of Thought. NJ: Erlbaum. [3]Avrunin, G.S., Corbett, J.C., & Dillon, L.K. (1998). Analysing Partially-Implemented Real-Time Systems. IEEE Transactions on Software Engineering, 24, 8, 602-614. [4]Barsalou, L.W. (1999). Perceptual Symbol Systems. Behavioral and Brain Sciences, 22, 577-660. [5]Biederman, I. (1985). Human Image Understanding: Recent research and a theory. Computer Vision, Graphics, and Image Processing 32, 29-73. [6]Carpenter, G.A. and Grossberg, S. (1988). The ART of Adaptive Pattern Recognition by a Self-Organizing Neural Network, IEEE Computer, 3, pages 77-88, 1988. [7]Churchland, P.S., and Sejnowski, T.J. (1992). The Computational Brain. Cambridge, Mass: MIT Press. [8]Coward, L. A. (1990). Pattern Thinking, New York: Praeger. [9]Coward, L. A. (1997). The Pattern Extraction Hierarchy Architecture: a Connectionist Alternative to the von Neumann Architecture, in Mira., J., Morenzo-Diaz, R., and Cabestanz, J. (eds.) Biological and Artificial Computation: from Neuroscience to Technology, 634-43, Berlin: Springer. [10]Coward, L.A. (1999). The Recommendation Architecture: Relating Cognition to Physiology, in Riegler, A. and Peschl, M. (eds.) Understanding Representation in the Cognitive Sciences, 91-105, Plenum Press. [11]Coward, L.A. (1999). A physiologically based approach to consciousness, New Ideas in Psychology, 17, 3, pages 271-290, 1999. [12]Coward, L.A. (1999). A physiologically based theory of consciousness, in Jordan, S. (ed.), Modeling Consciousness Across the Disciplines, pages 113-178, Maryland: UPA. [13]Coward, L.A. (2000). A Functional Architecture Approach to Neural Systems. International Journal of Systems Research and Information Systems, 9, pages 69-120, 2000. [14]Coward, L.A. and Gedeon, T. (2000). Optimization of Architectural Parameters in a Simulated Recommendation Architecture, in press. [15]Feigenbaum, E.A. and Simon, H. A. (1984). EPAM-like models of recognition and learning. Cognitive Science 8, 305-336. [16]Fraley, C. and Raftery, A.E. (1998). How Many Clusters? Which Clustering Method? Answers Via Model-Based Cluster Analysis. Technical Report No. 329, Department of Statistics, University of Washington. [17]French, R.M. (1997). Pseudo-recurrent connectionist networks: An approach to the "sensitivity-stability" dilemma. Connection Sciences 9(4), 353-379. [18]French, R.M. (1999). Catastrophic Forgetting in Connectionist Networks. Trends in Cognitive Science 3(4), 128-135. [19]Garlan, D., Allen, R. and Ockerbloom, J. (1995). Architectural Mismatch or Why it’s hard to build systems out of existing parts. IEEE Computer Society 17th International Conference on Software Engineering. New York: ACM. [20]Gedeon, T., Coward, L. A., and Bailing, Z. (1999). Results of Simulations of a System with the Recommendation Architecture, Proceedings of the 6th International Conference on Neural Information Processing, Volume I, pages 78-84. [21]Grossberg, S. (1987). Competitive Learning from interaction to adaptive resonance. Cognitive Science 11, pages 23-63, 1987. [22]Honkela, T, Pulkki, V. and Kohonen, T. (1995). Contextual Relations of Words in Grimm Tales, Analyzed by Self-Organizing Map, in Fogelman-Soulie, F. and Gallinari, P. (eds.), ICANN-95 Proceedings of International Conference on Artificial Neural Networks, 2, pages 3-7. Paris: EC2 et Cie. [23]Hopfield, J.J. (1982). Neural Networks and Physical Systems with Emergent Collective Computational Abilities. Proceedings of the National Academy of Sciences 79, 2554-8. [24]Johnson-Laird, P.N. (1983). Mental Models. Cambridge, Mass.: Harvard University Press. [25]Kaufman, L. and Rousseeuw, P.J. (1990). Finding Groups in Data. New York: Wiley. [26]Marr, D. (1991). From the Retina to the Cortex: Selected Papers of David Marr. Edited by L. M. Vaina. Boston: Birkhauser. [27]McClelland, J., McNaughton, B., and O’Reilly, R. (1995). Why are there complementary learning systems in the hippocampus and neocortex: Insights from the successes and failures of connectionist models of learning and memory. Psychological Review. 102, 419 – 457. [28]Newell, A. and Simon, H.A. (1972). Human Problem Solving. Englewood Cliffs, NJ.: Prentice-Hall. [29]Robins, A.(1995). Catastrophic forgetting, rehearsal, and pseudorehearsal. Connection Science 7, 123 – 146. [39]Rumelhart, D.E., Hinton, G.E., and Williams, R.J. (1986). Learning Representations by Back-propagating Errors. Nature 323, 533-6. [31]Sabisch, T., Ferguson, A. and Bolouri, H. (1997). Automatic registration of complex images using a self organizing neural system. IEEE International Joint Conference on Neural Networks, Anchorage, Alaska. [32]Sabisch, T., Ferguson, A. and Bolouri, H. (1998). Rotation, translation and scaling tolerant recognition of complex shapes using a hierarchical self organizing neural network. Proceedings of International Conference on Neural Information Processing 2, pages 1174-78. Berlin: Springer. [33]Solomon, K.O. amd Barsalou, L.W. (2000). Representing Properties Locally. Cognitive Psychology, in press. [34]Soni, D., Nord, R.L. and Hofmeister, C. (1995). Software Architecture in Industrial Applications. Proceedings of the 17th International Conference in Software Engineering, pages 196-207. New York: ACM. [35]Sterelny, K. (1990). The Representational Theory of Mind. Oxford: Basil Blackwell. [36]Stillings, N.A., Weisler, S.E., Chase, C.H., Feinstein, M.H., Garfield, J.L. and Rissland, E.L. (1995). Cognitive Science: An Introduction. Cambridge, Mass.: MIT Press. [37]Sutton, R.S. and Barto, A.G. (1998). Reinforcement Learning: An Introduction. Cambridge, MA.: MIT Press. [38]Treisman, A.M. and Gelade, G. (1980). A Feature Integration Theory of Attention. Cognitive Psychology 12, 97-136. [39]Willshaw, D., Hallam, J., Gingell. S., and Lau, Soo Leng (1997). Marr's Theory of the Neocortex as a Self-Organizing Neural Network. Neural Computation 9, pages 911-936, 1997. citation: coward, l andrew (2001) The Recommendation Architecture: Lessons from Large-Scale Electronic Systems Applied to Cognition. [Journal (Paginated)] document_url: http://cogprints.org/2300/3/RecArchLessons.pdf