Skip to main content
SpringerLink
Log in

The Gap Between Symbolic and Connectionist Approaches

  • Chapter
  • First Online:
A Geometric Approach to the Unification of Symbolic Structures and Neural Networks

Part of the book series: Studies in Computational Intelligence ((SCI,volume 910))

  • 843 Accesses

Abstract

For  symbolists, the way of thinking can be fully symbolically simulated without biological embodiment. For connectionists, biological embodiment is a must, and they use connectionist networks for embodiments.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 109.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 139.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 139.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    In localist representation, an entity (a concept) is represented by one node, which can be viewed as a one-element vector.

  2. 2.

    A Triple in knowledge-graph takes the form that consists of (head, relation, tail).

  3. 3.

    Neural-Symbolic Learning and Reasoning http://www.neural-symbolic.org/.

References

  • Adams, F., Aizawa, K., & Fuller, G. (1992). Rules in programming languages and networks. In The symbolic and connectionist paradigms: Closing the gap (pp. 49–68). Hillsdale NJ: Erlbaum.

    Google Scholar 

  • Adamson, M. J., & Damper, R. I. (1999). B-RAAM: A connectionist model which develops holistic internal representations of symbolic structures. Connection Science, 11(1), 41–71.

    Article  Google Scholar 

  • Aizawa, K. (1992). Biology and sufficiency in connectionist theory. In The symbolic and connectionist paradigms: Closing the gap (pp. 69–88). Hillsdale, NJ: Erlbaum.

    Google Scholar 

  • Bader, S., Hitzler, P., Hölldobler, S., & Witzel, A. (2007). A fully connectionist model generator for covered first-order logic programs. In IJCAI 2007, Proceedings of the 20th International Joint Conference on Artificial Intelligence (pp. 666–671), Hyderabad, India, 6–12 January 2007.

    Google Scholar 

  • Barlow, H. (1972). Single units and sensation: A neuron doctrine for perceptual psychology? Perception, 1, 371–394.

    Article  Google Scholar 

  • Bechtel, W., & Abrahamsen, A. (2002). Connectionism and the mind: Parallel processing, dynamics, and evolution in networks. Hong Kong: Graphicraft Ltd.

    Google Scholar 

  • Besold, T. R., d’Avila Garcez, A., & Lamb, L. C. (2017). Human-like neural-symbolic computing (Dagstuhl Seminar 17192). Dagstuhl Reports, 7(5), 56–83.

    Google Scholar 

  • Chalmers, D. J. (1992). Subsymbolic computation and the Chinese room. In The symbolic and connectionist paradigms: Closing the gap (pp. 25–48). Hillsdale, NJ: Erlbaum.

    Google Scholar 

  • Clarke, B. L. (1981). A calculus of individuals based on ‘connection’. Notre Dame Journal of Formal Logic, 23(3), 204–218.

    Article  MathSciNet  Google Scholar 

  • Clarke, B. L. (1985). Individuals and points. Notre Dame Journal of Formal Logic, 26(1), 61–75.

    Article  MathSciNet  Google Scholar 

  • Dinsmore, J. (1992). Thunder in the gap. In The symbolic and connectionist paradigms: Closing the gap (pp. 1–23). Erlbaum.

    Google Scholar 

  • Dong, T. (2007). The nine comments on the RCC theory. AAAI’07 Workshop on Spatial and Temporal Reasoning (pp. 16–20). Canada: Vancouver.

    Google Scholar 

  • Dong, T. (2008). A comment on RCC: From RCC to RCC++. Journal of Philosophical Logic, 37(4), 319–352.

    Article  MathSciNet  Google Scholar 

  • Dong, T. (2012). Recognizing variable environments—The theory of cognitive prism, volume 388 of Studies in computational intelligence. Berlin, Heidelberg: Springer.

    Google Scholar 

  • Dong, T., & Guesgen, H. (2007). Is an orientation relation a distance comparison relation? In IJCAI’07 Workshop on Spatial and Temporal Reasoning (pp. 45–51), Hyderabad, India.

    Google Scholar 

  • Dyer, M. G. (1988). The promise and problems of connectionism. Behavioral and Brain Sciences, 1, 32–33.

    Article  Google Scholar 

  • Fodor, J. A., & Pylyshyn, Z. W. (1988). Connectionism and cognitive architecture—A critical analysis. Cognition, 28(1–2), 3–71.

    Article  Google Scholar 

  • Frank, A. (1991). Qualitative spatial reasoning with cardinal directions. In Proceedings of the Seventh Austrian Conference on Artificial Intelligence (pp. 157–167). Berlin, Wien: Springer.

    Google Scholar 

  • Frank, A. (1992). Qualitative spatial reasoning about distances and orientations in geographic space. Journal of Visual Language and Computing, 3, 343–371.

    Article  Google Scholar 

  • Freeman, W. J. (1988). Dynamic systems and the “subsymbolic level”. Behavioral and Brain Sciences, 1, 33–34.

    Article  Google Scholar 

  • Freksa, C. (1992). Using orientation information for qualitative spatial reasoning. In Proceedings of the International Conference GIS-From Space to Territory: Theories and Methods of Spatial-Temporal Reasoning, LNCS. Pisa: Springer.

    Google Scholar 

  • Giles, C. L. and Gori, M. (Eds.). (1998). Adaptive processing of sequences and data structures, international summer school on neural networks, “E.R. Caianiello”—Tutorial lectures, London, UK, UK: Springer.

    Google Scholar 

  • Hinton, G. E. (1981). Implementing semantic networks in parallel hardware. In G. E. Hinton & J. A. Anderson (Eds.), Parallel models of associative memory (pp. 161–187). Hillsdale, NJ: Erlbaum.

    Google Scholar 

  • Hinton, G. E. (1986). Learning distributed representations of concepts. In Proceedings of the Eighth Annual Conference of the Cognitive Science Society (Vol. 1, p. 12), Amherst, MA.

    Google Scholar 

  • Hinton, G. E. (1990). Mapping part-whole hierarchies into connectionist networks. Artificial Intelligence, 46(1–2), 47–75.

    Article  Google Scholar 

  • Hopfield, J. J. (1982). Neural networks and physical systems with emergent collective computational abilities. Proceedings of the National Academy of Sciences of the United States of America, 79(8), 2554–2558.

    Article  MathSciNet  Google Scholar 

  • Newell, A. (1990). Unified theories of cognition. Cambridge, MA: Harvard University Press.

    Google Scholar 

  • Pinker, S., & Prince, A. (1988). On language and connectionism: Analysis of a parallel distributed processing model of language acquisition. Cognition, 28, 73–193.

    Google Scholar 

  • Pollack, J. B. (1990). Recursive distributed representations. Artificial Intelligence, 46(1–2), 77–105.

    Article  Google Scholar 

  • Randell, D., Cui, Z., & Cohn, A. (1992). A spatial logic based on regions and connection. In B. Nebel, W. Swartout, & C. Rich (Eds.), Proceeding of the 3rd International Conference on Knowledge Representation and Reasoning (pp. 165–176). San Mateo: Morgan Kaufmann.

    Google Scholar 

  • Renz, J., & Mitra, D. (2004). Qualitative direction calculi with arbitrary granularity. In C. Zhang, H. Guesgen, & W. Yeap (Eds.), PRICAI 2004: Trends in Artificial Intelligence: 8th Pacific Rim International Conference on Artificial Intelligence (pp. 65–74). Berlin, Heidelberg and New Zealand: Springer.

    Google Scholar 

  • Rosch, E. (1973). Natural categories. Cognitive Psychology, 3, 328–350.

    Article  Google Scholar 

  • Rumelhart, D. E., McClelland, J. L., & PDP Research Group (Eds.). (1986). Parallel distributed processing: Explorations in the microstructure of cognition, Vol. 1: Foundations. Cambridge, MA, USA: MIT Press.

    Google Scholar 

  • Searle, J. (1980). Minds, brains, and programs. Behavioral and Brain Sciences, 3(3), 417–457.

    Article  Google Scholar 

  • Smolensky, P. (1988). On the proper treatment of connectionism. Behavioral and Brain Sciences, 1, 1–23.

    Google Scholar 

  • Sun, R. (2002). Hybrid connectionist symbolic systems. In M. Arbib (Ed.), Handbook of brain theories and neural networks (2nd ed., pp. 543–547). Cambridge, MA: MIT Press.

    Google Scholar 

  • Sun, R. (2016). Implicit and explicit processes: Their relation, interaction, and competition. In L. Macchi, M. Bagassi, & R. Viale (Eds.), Cognitive unconscious and human rationality (pp. 27–52). Cambridge, MA: MIT Press.

    Google Scholar 

  • Sun, R., & Alexandre, F. (Eds.). (1997). Connectionist-symbolic integration: From unified to hybrid approaches. Hillsdale, NJ, USA: L. Erlbaum Associates Inc.

    Google Scholar 

  • Sun, R., & Bookman, L. A. (1994). Computational architectures integrating neural and symbolic processes: A perspective on the state of the art. Norwell, MA, USA: Kluwer Academic Publishers.

    Book  Google Scholar 

  • Sun, R., & Peterson, T. (1998). Autonomous learning of sequential tasks: Experiments and analyses. IEEE Transactions on Neural Networks, 9(6), 1217–1234.

    Article  Google Scholar 

  • Tversky, A. (1977). Features of similarity. Psychological Review, 84, 327–353.

    Article  Google Scholar 

  • Tversky, A., & Kahneman, D. (1974). Judgment under uncertainty: Heuristics and biases. Science, 185, 1124–1131.

    Article  Google Scholar 

  • Willshaw, D. J., Buneman, O. P., & Longuet-Higgins, H. C. (1969). Non-holographic associative memory. Nature, 222, 960–962.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. ML2R Competence Center for Machine Learning Rhine-Ruhr, MLAI Lab, AI Foundations Group, Bonn-Aachen International Center for Information Technology (b-it), University of Bonn, Bonn, Germany

    Tiansi Dong

Authors
  1. Tiansi Dong
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Tiansi Dong .

Rights and permissions

Reprints and permissions

Copyright information

© 2021 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG

About this chapter

Check for updates. Verify currency and authenticity via CrossMark

Cite this chapter

Dong, T. (2021). The Gap Between Symbolic and Connectionist Approaches. In: A Geometric Approach to the Unification of Symbolic Structures and Neural Networks. Studies in Computational Intelligence, vol 910. Springer, Cham. https://doi.org/10.1007/978-3-030-56275-5_2

Download citation

Publish with us

Policies and ethics

Search

Navigation