Abstract
This paper introduces a neuro-symbolic classification algorithm inspired by the SUSTAIN model in cognitive psychology. The proposed algorithm is implemented using neural cell assemblies, which can be seen as an intermediate level between individual neurons and higher-level cognitive functions. They offer the advantages of neural representations but can also be interpreted symbolically. Two methods are introduced to transform inputs into cell assembly representations. The algorithm creates prototypes from training instances and automatically estimates the weights of the problem dimensions. Although prototypes are typically used to classify new instances based on similarity, the paper also suggests a method to extract explicit, simple rules from the prototypes, encoded using the same cell assembly representation.
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
References
LeCun, Y.: A path towards autonomous machine intelligence (2022). https://openreview.net/pdf?id=BZ5a1r-kVsf. Accessed 15 Feb 2024
Goyal, A., Bengio, Y.: Inductive biases for deep learning of higher-level cognition. Proceedings. Math. Phys. Eng. Sci. 478(2266) (2022). https://doi.org/10.1098/rspa.2021.0068
Seo, S., Arik, S.O., Yoon, J., Zhang, X., Sohn, K., Pfister, T.: Controlling neural networks with rule representations. arXiv [cs.LG] (2021). http://arxiv.org/abs/2106.07804
Evans, R., Grefenstette, E.: Learning explanatory rules from noisy data. J. Artif. Intell. Res. 61, 1–64 (2018). https://doi.org/10.1613/jair.5714
Mao, J., Gan, C., Kohli, P., Tenenbaum, J. B., Wu, J.: The neuro-symbolic concept learner: interpreting scenes, words, and sentences from natural supervision. arXiv [cs.CV] (2019). http://arxiv.org/abs/1904.12584
Santoro, A., et al.: A simple neural network module for relational reasoning. arXiv [cs.CL] (2017). http://arxiv.org/abs/1706.01427
Yu, D., Yang, B., Liu, D., Wang, H., Pan, S.: A survey on neural-symbolic learning systems. Neural Networks: Off. J. Int. Neural Network Soc. 166, 105–126 (2023). https://doi.org/10.1016/j.neunet.2023.06.028
Hassabis, D., Kumaran, D., Summerfield, C., Botvinick, M.: Neuroscience-inspired artificial intelligence. Neuron 95(2), 245–258 (2017). https://doi.org/10.1016/j.neuron.2017.06.011
Leon, F.: A review of findings from neuroscience and cognitive psychology as possible inspiration for the path to artificial general intelligence. arXiv [cs.AI] (2024). http://arxiv.org/abs/2401.10904
Shepard, R.N., Hovland, C.I., Jenkins, H.M.: Learning and memorization of classifications. Psychol. Monographs 75(13), 1–42 (1961). https://doi.org/10.1037/h0093825
Love, B. C., Medin, D. L., Gureckis, T. M.: SUSTAIN: a network model of category learning. Psychol. Rev. 111(2), 309–332 (2004). https://doi.org/10.1037/0033-295x.111.2.309
Grossberg, S.: Adaptive Resonance Theory: How a brain learns to consciously attend, learn, and recognize a changing world. Neural Networks Off. J. Int. Neural Network Soc. 37, 1–47. https://doi.org/10.1016/j.neunet.2012.09.017 (2013)
Pham, D.T., Aksoy, M.S.: RULES: a simple rule extraction system. Expert Syst. Appl. 8(1), 59–65 (1995). https://doi.org/10.1016/s0957-4174(99)80008-6
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Leon, F. (2024). A Neuro-Symbolic Classification Algorithm Using Neural Cell Assemblies. In: Nguyen, NT., et al. Advances in Computational Collective Intelligence. ICCCI 2024. Communications in Computer and Information Science, vol 2166. Springer, Cham. https://doi.org/10.1007/978-3-031-70259-4_19
Download citation
DOI: https://doi.org/10.1007/978-3-031-70259-4_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-70258-7
Online ISBN: 978-3-031-70259-4
eBook Packages: Computer ScienceComputer Science (R0)