Abstract
Hybrid connectionist symbolic systems have been the subject of much recent research in AI. By focusing on the implementation of high-level human cognitive processes (e.g., rule-based inference) on low-level, brain-like structures (e.g., neural networks), hybrid systems inherit both the efficiency of connectionism and the comprehensibility of symbolism. This paper presents the Basic Reasoning Applicator Implemented as a Neural Network (BRAINN). Inspired by the columnar organisation of the human neocortex, BRAINN’s architecture consists of a large hexagonal network of Hopfield nets, which encodes and processes knowledge from both rules and relations. BRAINN supports both rule-based reasoning and similarity-based reasoning. Empirical results demonstrate promise.
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
Bogacz, R., Giraud-Carrier, C.: BRAINN: A Connectionist Approach to Symbolic Reasoning. In: Proceedings of the First International ICSC Symposium on Neural Computation (NC 1998), pp. 907–913 (1998)
Boz, O.: Bibliography on Integration of Symbolism with Connectionism, and Rule Integration and Extraction in Neural Networks. (1997), http://www.lehigh.edu/ob00/integrated/references-new.html
Calvin, W.: The Cerebral Code. MIT Press, Cambridge (1996)
Hall, L.O., Romaniuk, S.G.: A Hybrid Connectionist, Symbolic Learning System. In: Proceedings of the National Conference on Articial Intelligence (AAAI 1990), pp. 783–788 (1990)
Herz, J., Krogh, A., Palmer, R.: Introduction to the Theory of Neural Computation. Addison-Wesley, Reading (1991)
Hinton, G.: Implementing Semantic networks in Parallel Hardware. In: Hinton, G., Anderson, J. (eds.) Parallel Models of Associative Memory. Lawrence Erlbaum Associates, Inc, Mahwah (1981)
Hopfield, J., Tank, D.: Neural Computation of Decisions in Optimization Problems. Biological Cybernetics 52, 141–152 (1985)
Lifschitz, V.: Benchmark Problems for Formal Nonmonotonic Reasoning. In: Reinfrank, M., Ginsberg, M.L., de Kleer, J., Sandewall, E. (eds.) Non-Monotonic Reasoning 1988. LNCS, vol. 346, pp. 202–219. Springer, Heidelberg (1988)
Martinez, T.R.: Adaptive Self-Organizing Networks. Ph.D. Thesis (Tech. Rep. CSD 860093), University of California, Los Angeles (1986)
Sun, R.: A Connectionist Model for Common Sense Reasoning Incorporating Rules and Similarities. Knowledge Acquisition 4, 293–331 (1992)
Sun, R.: Bibliography on Connectionist Symbolic Integration. In: Sun, R. (ed.) Computational Architectures Integrating Symbolic and Connectionist Processing. Kluwer Academic Publishers, Dordrecht (1994)
Sun, R., Alexandre, F. (eds.): Working Notes of IJCAI 1995 Workshop on Connectionist-Symbolic Integration (1995)
Sun, R.: Learning, Action and Consciousness: A Hybrid Approach Toward Modeling Consciousness. Neural Networks 10(7), 1317–1331 (1997)
Touretzky, D., Hinton, G.: Symbols Among the Neurons: Details of a Connectionist Inference Architecture. In: Proceedings of the International Joint Conference on Articial Intelligence (IJCAI 1985), pp. 238–243 (1985)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bogacz, R., Giraud-Carrier, C. (2000). A Novel Modular Neural Architecture for Rule-Based and Similarity-Based Reasoning. In: Wermter, S., Sun, R. (eds) Hybrid Neural Systems. Hybrid Neural Systems 1998. Lecture Notes in Computer Science(), vol 1778. Springer, Berlin, Heidelberg. https://doi.org/10.1007/10719871_5
Download citation
DOI: https://doi.org/10.1007/10719871_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-67305-7
Online ISBN: 978-3-540-46417-4
eBook Packages: Springer Book Archive