Connectionist networks qua graphs. (English) Zbl 0645.68090
There is a lot of excitement in the field of artificial intelligence (AI) at the moment centering around the ideas of “connectionism”. Connection networks are used to represent knowledge in terms of “subsymbolic” nodes (i.e. a single node does not by itself represent a conceptual entity, such as a dog, apple, Mary; any node may participate in a number of patterns of activation and each such pattern is a representation of a conceptual entity). The edges of these networks are arcs, with an associated numerical weight, whose role is to transfer “activity” from one node to another according to some function of the arc weights. The phenomenon of learning is typically modeled by adjusting arc weights according to some function of the network’s desired and observed performance.
The connectionist paradigm is seen as a promizing new approach to the realization of intelligent systems, and one that may be particularly amenable to formal analysis. This paper introduces connectionism, points out some of the major problems and argues that a graph theoretical approach to some of the recognized problems may prove fruitful.
The connectionist paradigm is seen as a promizing new approach to the realization of intelligent systems, and one that may be particularly amenable to formal analysis. This paper introduces connectionism, points out some of the major problems and argues that a graph theoretical approach to some of the recognized problems may prove fruitful.
MSC:
| 68T05 | Learning and adaptive systems in artificial intelligence |
| 92B05 | General biology and biomathematics |
| 94C15 | Applications of graph theory to circuits and networks |
| 68T99 | Artificial intelligence |
| 68R10 | Graph theory (including graph drawing) in computer science |
Keywords:
knowledge representation; Connection networks; learning; realization of intelligent systemsReferences:
| [1] | Woods, W. A., What’s in a link?, (Bobrow, D. G.; Collins, A., Representation and Understanding (1975), Academic Press: Academic Press New York) |
| [2] | Partridge, D., AI: Applications in the Future of Software Engineering (1986), Ellis Horwood/Wiley: Ellis Horwood/Wiley New York |
| [3] | Schvaneveldt, R. W.; Dearholt, D. W.; Durso, F. T., Graph theoretic foundations of Pathfinder networks, Comput. Math. Applic., 15, 4, 337-345 (1988) · Zbl 0647.92024 |
| [4] | Hebb, D. O., The Organization of Behavior (1949), Wiley: Wiley New York |
| [5] | Rosenblatt, F., Principles of Neurodynamics (1962), Spartan: Spartan New York · Zbl 0143.43504 |
| [6] | Minsky, M.; Papert, S., Perceptrons (1969), Press, MIT: Press, MIT Cambridge, Mass · Zbl 0197.43702 |
| [7] | Harary, F., Graph Theory (1969), Addison-Wesley: Addison-Wesley Reading, Mass · Zbl 0797.05064 |
| [8] | D. E. Rumelhart, G. E. Hinton and R. J. Williams, Learning internal representations by error propagation. In Parallel Distributed Processing; D. E. Rumelhart, G. E. Hinton and R. J. Williams, Learning internal representations by error propagation. In Parallel Distributed Processing |
| [9] | Sejnowski, T. J.; Rosenberg, D. R., NETtalk: a parallel network that learns to read aloud, (Technical Report JHU/EECS-86-01 (1986), Johns Hopkins University, Electrical Engineering and Computer Science: Johns Hopkins University, Electrical Engineering and Computer Science Baltimore) |
| [10] | (Hinton, G. E.; Anderson, J. A., Parallel Models of Associative Memory (1981), Erlbaum: Erlbaum Hillsdale, N.J) · Zbl 0685.68013 |
| [11] | Feldman, J. A., Connectionist models and their applications, Cog. Sci., 9, 1 (1985), (Guest Editor) |
| [12] | Pollack, J.; Waltz, D. L., Interpretation of natural language, Byte, 189-198 (1986), Feb. |
| [13] | Feldman, J. A., A connectionist model of visual memory, (Hinton, G. E.; Anderson, J. A., Parallel Models of Associative Memory (1981), Erlbaum: Erlbaum Hillsdale, NJ), 49-81 |
| [14] | Ackley, D. H.; Hinton, G. E.; Sejnowski, T. J., A learning algorithm for Boltzmann machines, Cog. Sci., 9, 1, 147-169 (1985) |
| [15] | Hage, P.; Harary, F., Structural Models in Anthropology (1983), Cambridge University Press |
| [16] | Rumelhart, D. E.; Zipser, D., Feature discovery by competitive learning, Cog. Sci., 9, 1, 75-112 (1985) |
| [17] | Johnston, V. S.; Partridge, D.; Lopez, P. D., A neural theory of cognitive development, J. Theor. Biol., 100, 3, 485-509 (1983) |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
