Abstract
The hybrid architectures described in chapters 3, 4, and 5 are based on fusion, transformation, and combination of intelligent methodologies like expert systems, fuzzy logic, neural networks, and genetic algorithms. The concepts of fusion, transformation, and combination have been used in different situations or tasks, and by applying top-down and/or bottom-up knowledge engineering strategy. All these hybrid architectures have a number of advantages in that the hybrid arrangement is able to successfully accomplish tasks in various situations. However, these hybrid architectures also suffer from some drawbacks. These drawbacks can be explained in terms of the quality of solution and range of tasks covered (see Figure 6.1). Fusion, and transformation architectures on their own do not capture all aspects of human cognition related to problem solving. For example, fusion architectures result in conversion of explicit knowledge into implicit knowledge, and thus loose on the declarative aspects of problem solving. Thus, they are restricted in terms of the range of tasks covered by them. The transformation architectures with bottom up strategy get into problems with increasing task complexity. Therefore the quality of solution suffers when there is heavy overlap between variables, where the rules are very complicated, the quality of data is poor, or data is noisy. Also, because they lack explicit reasoning, the range of tasks covered by them becomes restricted. The combination architectures cover a range of tasks because of their inherent flexibility in terms of selection of two or more intelligent methodologies.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Arbib, M. A. (1987), Brains, Machines and Mathematics, Springer Verlag, New York.
Beale, R. and Jackson, T. (1990), Neural Computing: An Introduction, Bristol: Hilger.
Bezdek, J.C. (1994), “What is Computational Intelligence?,” Computational Intelligence Imitating Life, IEEE Press, New York.
Chandrasekaran, B. (1990), “What kind of information processing is intelligence,” Foundations of Artificial Intelligence, Cambridge University Press, pp14–45.
Chandrasekaran, B., Johnson, T. R. and Smith, J. W. (1992), “Task-Structure Analysis for Knowledge Modeling,” Communications of the ACM, September, vol. 35, no. 9., pp. 124–137.
Churchland, P.M. (1990), “Representation and High-Speed Computation in Neural Networks,” Foundations of Artificial Intelligence, Cambridge University Press, USA.
Fieldman, J. (1988), “Neural Representation of Conceptual Knowledge,” Neural Connections, Mental Computation, MIT Press, pp. 69–103.
Fodor, J. A. (1983), The Modularity of Mind, MIT Press.
Fodor, J.A., and Plyshyn, Z. W. (1988), “Connectionism and Cognitive Architecture: A Critical Analysis,” Cognition, 28:2–71.
Khosla, R. and Dillon, T. (1992), “A Neuro-Expert System Architecture with Applications to Alarm Processing in a Power System Control Centre,” Fourth International IEEE conference on Tools for Artificial Intelligence, Arlington, Virginia, USA.
Khosla, R. and Dillon, T. (1992b) “An Integrated Neuro-Expert System Model for Real-Time Systems” International Joint Conference on Neural Networks, IJCNN’92, Beijing, China, vol. 1, pp. 154–159.
Khosla, R. and Dillon, T. (1993) “Task Decomposition and Competing Expert System-Artificial Neural Net Objects for Reliable and Real Time Inference,” International IEEE Conference on Neural Networks, San Francisco, USA, pp794–800, Mar/Apr.
Khosla, R. and Dillon, T. (1994a) “Learning Knowledge and Strategy of a Generic Neuro-Expert System Model,” AAAI International Symposium on Integrating Knowledge and Neural Heuristics, Florida, USA.
Khosla, R. and Dillon, T. (1994b), “Cognitive and Computational Foundations of Symbolic-Connectionist Integration,” ECAI’94 Workshop Proceedings on Symbolic-Connectionist Processing, Netherlands, Holland.
Khosla, R. and Dillon, T. (1994c) “Constructs for Building Complex Symbolic-Connectionist Systems,” Sixth IEEE conference on Tools with Artificial Intelligence, New Orleans, Lousiana, USA.
Khosla, R. and Dillon, T. (1994d) “A Distributed Real-Time Alarm Processing System with Symbolic-Connectionist Computation,” Proceedings of IEEE Workshop in Real Time Systems, July, Washington D.C., USA.
Khosla, R. and Dillon, T. (1995), “Task Structure and Computational Level: Architectural Issues in Symbolic-Connectionist Integration,” Working Notes of IJCAI95 Workshop on Connectionist-Symbolic Integration: From Unified to Hybrid Approaches, Montreal, Canada.
Khosla, R. and Dillon, T. (1997), “Learning Knowledge and Strategy of a Generic Neuro-Expert System Architecture in Alarm Processing,” to appear in IEEE Transactions in Power Systems.
Laird, J., Rosenbloom, P. and Newell, A. (1987), “SOAR: An Architecture for General Intelligence,” Artificial Intelligence, vol. 33, pp. 1–64.
Laird, J. E., Yager, E.S., Hucka, M., and Tuck, M. (1991), “Robo-Soar: An integration of External Interaction, Planning, and Learning using Soar,” Robotics and Autonomous Systems, vol. 8, pp. 113–129.
Lallement, Y., Hilario, M., and Alexandre, F. (1995), “Neurosymbolic Integration: Cognitive Grounds and Computational Strategies,” World Conference on the Fundamentals of Artificial Intelligence, Paris, France.
Lallement, Y., and Alexandre, F. (1995), “Cognitive Aspects of Neurosymbolic Integration,” Working notes of the Workshop on Connectionist-Symbolic Integration: From Unified to Hybrid Approaches, Montreal, Canada, pp. 7–11.
Malsburg, V. D. (1988), Goal and Architecture of Neural Computers, Neural Computers, Springer Verlag, Berlin, West Germany.
McClelland, J. L., Rumelhart, D. E. and Hinton, G.E. (1986), “The Appeal of Parallel Distributed Processing,” Parallel Distributed Processing, vol. 1, pp. 3–40.
McClelland, J. L., Rumelhart, D. E. and Hinton, G.E. (1986), Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol. 2, Cambridge, MA: The MIT Press.
Medskar, L. A. (1995), “Hybrid Intelligent Systems,” Kluwer Academic Publishers, Massachusetts, USA.
Minsky, M., (1991), “Logical Versus Analogical or Symbolic Versus Connec-tionist or Neat Versus Scruffy,” AI Magazine, 12(2), pp. 34–51.
Mitchell, T. M. (1990), “Becoming Increasingly Reactive (Mobile Robots),” Proceedings of the Eighth National Conference on Artificial Intelligence (AAAI90), vol. 2 pp. 1051–1058.
Newell, A., and Simon, H. A. (1972), “The Theory of Human Problem Solving,” Human Problem Solving, Englewood Cliffs, NJ: Prentice Hall.
Newell, A. (1980), “Physical symbol Systems,” Cognitive Science, vol. 4, pp. 135–183.
Newell, A. and Rosenbloom, P. S. (1981), “Mechanisms of Skill Acquisition and the Learning in Practice,” Cognitive Skills and their Acquisition, J. R. Anderson (Ed.), Hillsdale, NJ: Erlbaum
Newell, A. (1981), “The Knowledge Level,” AI, pp. 1–19.
Newell, A. (1990), Unified Theories of Cognition, Harvard University Press, Cambridge, Massachusetts, USA
Rao, R.P.N. and Ballard, D. (1995), “Dynamic Model of Visual Memory Predicts Neural Response Properties In The Visual Cortex,” Technical Report 95.4, National Resource Laboratory for the study of Brain and Behavior, Department of Computer Science, University of Rochester, Rochester, USA.
Russell, S., and Norvig, P. (1995), Artificial Intelligence — A Modern Approach, Prentice Hall, New Jersey, USA.
Shepard, R.N., 1988, “Internal Representations of Universal Regularities: A Challenge for Connectionism,” Neural Connections, Mental Computation, MIT Press, pp. 104–135.
Smolensky, P., (1990) “Connectionism and Foundations of AI,” Foundations of Artificial Intelligence, Cambridge University Press, pp. 306–327.
Soucek, B., and the IRIS Group (eds) (1991), Neural and Intelligent Systems Integration, John Wiley and Sons, New York, USA.
Sun, R., (1991), “Integrating Rules and Connectionism for Robust Reasoning,” Brandeis University, Computer Science Department, Waltham, MA, TR-CS-90-154, January, USA.
Tang, S. K., Dillon, T. and Khosla, R. (1995a), “Fuzzy Logic and Knowledge Representation in a Symbolic-Subsymbolic Architecture,” 1995, IEEE Inte-national Conference on Neural Networks, Perth, Australia
Tang, S. K., Dillon, T. and Khosla, R. (1995b) “Application of an Integrated Fuzzy, Knowledge-Based, Connectionist Architecture for Fault Diagnosis in Power Systems,” Sixth IEEE Intelligent Systems Applications Conference, Florida, USA.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1997 Springer Science+Business Media New York
About this chapter
Cite this chapter
Khosla, R., Dillon, T. (1997). Association Systems — Task Structure Level Associative Hybrid Architecture. In: Engineering Intelligent Hybrid Multi-Agent Systems. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-6223-8_6
Download citation
DOI: https://doi.org/10.1007/978-1-4615-6223-8_6
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-7854-9
Online ISBN: 978-1-4615-6223-8
eBook Packages: Springer Book Archive