Abstract
The function of the mind consists of two different types, namely, System 1 and System 2 (Kahneman in Thinking, fast and slow. Allen Lane, Penguin Books, 2011). The basic function of System 1 (fast thinking) is associative activation.
I advocate a third form of representing information that is based on using geometrical structures rather than symbols or connections among neurons.
—(Gärdenfors 2000, p. 2)
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The Third Law of Cognition: Feeling comes first (Tversky 2019, p. 42).
- 2.
The Seventh Law of Cognition: The mind fills in missing information (Tversky 2019, pp. 78, 244).
- 3.
Dyer (1988) called this “connectoplasm”.
- 4.
Connectionism is a special case of associationism that models associations using artificial neuron networks (Gärdenfors 2000, p. 1).
References
Bordes, A., Usunier, N., Garcia-Duran, A., Weston, J., & Yakhnenko, O. (2013). Translating embeddings for modelling multi-relational data. In C. J. C. Burges, L. Bottou, M. Welling, Z. Ghahramani, & K. Q. Weinberger (Eds.), Advances in neural information processing systems (Vol. 26, pp. 2787–2795). Curran Associates, Inc.
Byrne, R. W. (1979). Memory for urban geography. Quarterly Journal of Experimental Psychology, 31, 147–154.
Dinsmore, J. (1992). Thunder in the gap. In The symbolic and connectionist paradigms: Closing the gap (pp. 1–23). Hillsdale, NJ: Erlbaum.
Dong, T., Wang, Z., Li, J., Bauckhage, C., & Cremers, A. B. (2019a). Triple classification using regions and fine-grained entity typing. In Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19), (pp. 77–85), Honolulu, Hawaii, USA, 27 January–1 February 2019.
Dong, T., Bauckhage, C., Jin, H., Li, J., Cremers, O. H., Speicher, D., Cremers, A. B., & Zimmermann, J. (2019b). Imposing category trees onto word-embeddings using a geometric construction. In ICLR-19, New Orleans, USA. 6-9 May 2019.
Dreyfus, H. L., Dreyfus, S. E., & Athanasiou, T. (1986). Mind over machine: The power of human intuition and expertise in the era of the computer. New York, NY, USA: The Free Press.
Dyer, M. G. (1988). The promise and problems of connectionism. Behavioral and Brain Sciences, 1, 32–33.
Erk, K. (2009). Supporting inferences in semantic space: Representing words as regions. In IWCS-8’09 (pp. 104–115). Stroudsburg, PA, USA: Association for Computational Linguistics.
Faruqui, M., Dodge, J., Jauhar, S. K., Dyer, C., Hovy, E., & Smith, N. A. (2015). Retrofitting word vectors to semantic lexicons. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (pp. 1606–1615). ACL.
Feldman, J. (2006). From molecule to metaphor: A neural theory of language. Cambridge, MA: The MIT Press.
Fu, R., Guo, J., Qin, B., Che, W., Wang, H., & Liu, T. (2015). Learning semantic hierarchies: A continuous vector space approach. Transactions on Audio, Speech, and Language Processing, 23(3), 461–471.
Gärdenfors, P. (2000). Conceptual spaces—The geometry of thought. Cambridge, MA, USA: MIT Press.
Grady, J. (1997). Foundations of meaning: Primary metaphors and primary scenes, University Microfilms.
Harnad, S. (1990). The symbol grounding problem. Physics D, 42(1–3), 335–346.
Harnad, S. (2003). The symbol grounding problem. In Encyclopedia of cognitive science. Nature Publishing Group/Macmillan.
Hristov, Y., Penkov, S., Lascarides, A., & Ramamoorthy, S. (2017). Grounding symbols in multi-modal instructions. In Proceedings of the First Workshop on Language Grounding for Robotics (pp. 49–57). Vancouver, Canada: Association for Computational Linguistics.
Ji, G., He, S., Xu, L., Liu, K., & Zhao, J. (2015). Knowledge graph embedding via dynamic mapping matrix. In ACL’2015 (pp. 687–696). Beijing: ACL.
Kahneman, D. (2011). Thinking, fast and slow. Allen Lane, Penguin Books. Nobel laureate in Economics in 2002.
Lakoff, G., & Johnson, M. (1980). Metaphors We live by. Chicago: The University of Chicago Press. Citation is based on the reprinted in 2003.
Li, X., Vilnis, L., Zhang, D., Boratko, M., & McCallum, A. (2019). Smoothing the geometry of box embeddings. In International Conference on Learning Representations (ICLR).
Lin, Y., Liu, Z., Sun, M., Liu, Y., & Zhu, X. (2015). Learning entity and relation embeddings for knowledge graph completion. In AAAI’15 (pp. 2181–2187). AAAI Press.
McNamara, T. P. (1991). Memory’s view of space. The Psychology of Learning and Motivation, 27, 147–186.
Quillian, M. (1968). Semantic memory. In M. Minsky (Ed.), Semantic information processing. Cambridge, MA: MIT Press.
Regier, T. (1997). The human semantic potential: Spatial language and constrained connectionism. Cambridge, MA: The MIT Press.
Steels, L. (2008). The symbol grounding problem has been solved. So what’s next. In Symbols and embodiment: Debates on meaning and cognition (pp. 223–244). New Orleans, USA: Oxford University Press.
Stevens, A., & Coupe, P. (1978). Distance estimation from cognitive maps. Cognitive Psychology, 13, 526–550.
Sun, R. (2015). Artificial intelligence: Connectionist and symbolic approaches. In D. W. James (Ed.), International encyclopedia of the social and behavioral sciences (2nd ed., pp. 35–40). Oxford: Pergamon/Elsevier.
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. 27–257). Cambridge, MA: MIT Press.
Tversky, B. (1981). Distortions in memory for maps. Cognitive Psychology, 13, 407–433.
Tversky, B. (1992). Distortions in cognitive maps. Geoforum, 23(2), 131–138.
Tversky, B. (2019). Mind in motion. New York, USA: Basic Books.
Wang, Z., Zhang, J., Feng, J., & Chen, Z. (2014). Knowledge graph embedding by translating on hyperplanes. In AAAI (pp. 1112–1119). AAAI Press.
Author information
Authors and Affiliations
Corresponding author
Rights 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
Cite this chapter
Dong, T. (2021). Spatializing Symbolic Structures for the Gap. 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_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-56275-5_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-56274-8
Online ISBN: 978-3-030-56275-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)