Abstract
It is now more than a half-century since the Physical Symbol Systems Hypothesis (PSSH) was first articulated as an empirical hypothesis. More recent evidence from work with neural networks and cognitive architectures has weakened it, but it has not yet been replaced in any satisfactory manner. Based on a rethinking of the nature of computational symbols – as atoms or placeholders – and thus also of the systems in which they participate, a hybrid approach is introduced that responds to these challenges while also helping to bridge the gap between symbolic and neural approaches, resulting in two new hypotheses, one that is to replace the PSSH and the other focused more directly on cognitive architectures.
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
Similar content being viewed by others
Notes
- 1.
The CMC also allows numeric data, consideration of which is beyond the scope of this paper.
References
Newell, A., Simon, H.A.: Human Problem Solving. Prentice-Hall, Englewood Cliffs (1972)
Newell, A., Simon, H.A.: Computer science as empirical inquiry: symbols and search. Comm. ACM 19(3), 113–126 (1972)
Newell, A.: Physical symbol systems. Cog. Sci. 4(2), 135–183 (1980)
Laird, J.E., Lebiere, C., Rosenbloom, P.S.: A standard model of the mind: toward a common computational framework across artificial Intelligence, cognitive science, neuroscience, and robotics. AI Mag. 38(4), 13–26 (2017)
Rosenbloom, P.S., Demski, A., Ustun, V.: The Sigma cognitive architecture and system: towards functionally elegant grand unification. J. Artif. Gen. Intell. 7(1), 1–103 (2016)
Kurfess, F.J.: Integrating symbol-oriented and sub-symbolic reasoning methods into hybrid systems. In: Apolloni, B., Kurfess, F. (eds.) From Synapses to Rules: Disc. Sym. Rules from Neural Proc. Data, pp. 275–292. Kluwer, New York (2002)
Bader, S., Hitzler, P.: Dimensions of neural-symbolic integration—a structured survey. In: Artëmov, S.N., Barringer, H., d’Avila Garcez, A.S., Lamb, L.C., Woods, J. (eds.) We Will Show Them! Essays in Honour of Dov Gabbay, pp. 167–194. Coll. Pubs., Rickmansworth (2005)
Nilsson, N.J.: The physical symbol system hypothesis: status and prospects. In: Lungarella, M., Iida, F., Bongard, J., Pfeifer, R. (eds.) 50 Years of Artificial Intelligence. LNCS (LNAI), vol. 4850, pp. 9–17. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-77296-5_2
Goodfellow, I.J., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)
Koller, D., Friedman, N.: Probabilistic Graphical Models: Principles and Techniques. MIT Press, Cambridge (2009)
Kotseruba, I., Tsotsos, J.K.: 40 years of cognitive architectures: core cognitive abilities and practical applications. Artif. Intell. Rev. 53(1), 17–94 (2018). https://doi.org/10.1007/s10462-018-9646-y
Rosenbloom, P.S.: Thoughts on architecture. In: Goertzel, B., Iklé, M., Potapov, A., Ponomaryov, D. (eds.) Artificial General Intelligence (AGI 2022). LNCS, vol. 13539, pp. 364–373. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-19907-3_35
de Raedt, L., Kersting, K., Natarajan, S., Poole, D.: Statistical relational artificial intelligence: logic, probability, and computation. Synth. Lect. Artif. Intell. Mach. Learn. 10(2), 1–189 (2016)
Rosenbloom, P.S.: On theories and their implications for cognitive architectures (In prep.)
Dictionary.com on symbol. https://www.dictionary.com/browse/symbol. Accessed 15 Feb 2023
McDermott, D.V.: Mind and Mechanism. MIT Press, Cambridge (2001)
Sun, R.: The CLARION cognitive architecture: towards a comprehensive theory of the mind. In: Chipman, S. (ed.) The Oxford Handbook of Cognitive Science, pp. 117–133. Oxford University Press, New York (2017)
Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. Adv. Neural Inf. Process. Syst. 26, 3111–3119 (2013)
Hinton, G.E., McClelland, J.L., Rumelhart, D.E.: Distributed representations. In: McClelland, J.L., Rumelhart, D.E. (eds.) Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol. 1, pp. 77–109. MIT Press, Cambridge (1986)
Fodor, J.A., Pylyshyn, Z.W.: Connectionism and cognitive architecture: a critical analysis. Cognition 28(1–2), 3–71 (1988)
LeCun, Y., Bengio, Y.: Convolutional networks for images, speech, and time series. In: Arbib, M. (ed.) The Handbook of Brain Theory and Neural Nets. MIT Press, Cambridge (1995)
Vaswani, A., et al.: Attention is all you need. In: Proc. of the 31st Annual Conf. on Neural Info. Proc. Sys., pp. 5998–6008 (2017)
Brown, T.B., et al.: Language models are few-shot learners. In: Proc. of the 34th Conf. on Neural Info. Proc. Sys., pp. 1877–1901 (2020)
Siegelmann, H.T., Sontag, E.D.: Turing computation with neural nets. Appl. Math. Lett. 4(6), 77–80 (1991)
Tesauro, G.: Temporal difference learning and TD-Gammon. Comm. ACM 38(3), 58–68 (1995)
Silver, D., et al.: A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play. Science 362(6419), 1140–1144 (2018)
Penrose, R.: The Emperor’s New Mind: Concerning Computers, Minds, and The Laws of Physics. Oxford University Press, Oxford (1989)
Laskey, K.B.: Quantum physical symbol systems. J. Log. Lang. Inf. 15(1–2), 109–154 (2006)
Acknowledgements
I would like to think John Laird, Christian Lebiere, and Andrea Stocco for helpful comments and discussions on this general topic and this particular paper.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Rosenbloom, P.S. (2023). Rethinking the Physical Symbol Systems Hypothesis. In: Hammer, P., Alirezaie, M., Strannegård, C. (eds) Artificial General Intelligence. AGI 2023. Lecture Notes in Computer Science(), vol 13921. Springer, Cham. https://doi.org/10.1007/978-3-031-33469-6_21
Download citation
DOI: https://doi.org/10.1007/978-3-031-33469-6_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-33468-9
Online ISBN: 978-3-031-33469-6
eBook Packages: Computer ScienceComputer Science (R0)