Abstract
The Causal Cognitive Architecture 3 is a biologically inspired cognitive architecture based heavily on navigation maps—arrays holding spatial navigation information about the external environment but also coopted by the architecture for much of its data storage and representational requirements. Sensory information is stored in navigation maps and operated on in the architecture. Enhancement of feedback pathways in the architecture allows the intermediate results of operations on navigation maps to be re-processed in the next operating cycle and has been shown to allow the architecture to generate causal behavior. Here it is shown that this also can readily allow the emergence of analogical processing as a core mechanism in the architecture. If a navigation map cannot be processed to yield an actionable output, then it is compared to a similar navigation map and automatically an analogical result is produced which the architecture can possibly use as an output. Analogical processing as a core mechanism may be advantageous in creating more capable artificial general intelligence systems.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hofstadter, D.R.: Analogy as the core of cognition. In: Gentner, D., Holyoak, K.J., Kokinov, B.N. (eds.) The Analogical Mind, pp. 499–538. MIT Press (2001)
Schneider, H.: Causal cognitive architecture 1: integration of connectionist elements into a navigation-based framework. Cogn. Syst. Res. 66, 67–81 (2021). https://doi.org/10.1016/j.cogsys.2020.10.021
Schneider, H.: Causal cognitive architecture 3: a solution to the binding problem. Cogn. Syst. Res. 72, 88–115 (2022). https://doi.org/10.1016/j.cogsys.2021.10.004
Schneider, H.: The meaningful-based cognitive architecture model of schizophrenia. Cogn. Syst. Res. 59, 73–90 (2020). https://doi.org/10.1016/j.cogsys.2019.09.019
Falkenhainer, B., Forbus, K.D., Gentner, D.: The structure-mapping engine. In: Proceedings of the National Conference on Artificial Intelligence, AAAI, pp 272–277 (1986)
Hofstadter, D.R., Mitchell, M.: The copycat project. In: Holyoak, K.J., Barnden, J.A. (eds.) Advances in Connectionist and Neural Computation Theory, vol. 2, pp. 31–112 (1994). Ablex
Wu, Y., Dong, H., Grosse, R., Ba, J.: The Scattering Compositional Learner. arXiv:2007.04212 (2020). https://doi.org/10.48550/arXiv.2007.04212
Mitchell, M.: Abstraction and analogy-making in artificial intelligence. Ann. N Y Acad. Sci. 1505(1), 79–101 (2021). https://doi.org/10.1111/nyas.14619
Chollet, F.: On the Measure of Intelligence. arXiv:1911.01547 (2019)
Chen, Z., Sanchez, R., Campbell, T.: From beyond to within their grasp: analogical problem solving in 10- and 13-month-olds. Dev. Psychol. 33, 790–801 (1997). https://doi.org/10.1037//0012-1649.33.5.790
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
Schneider, H. (2023). Analogical Problem Solving in the Causal Cognitive Architecture. In: Goertzel, B., Iklé, M., Potapov, A., Ponomaryov, D. (eds) Artificial General Intelligence. AGI 2022. Lecture Notes in Computer Science(), vol 13539. Springer, Cham. https://doi.org/10.1007/978-3-031-19907-3_10
Download citation
DOI: https://doi.org/10.1007/978-3-031-19907-3_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19906-6
Online ISBN: 978-3-031-19907-3
eBook Packages: Computer ScienceComputer Science (R0)