Abstract
Category theory has been successfully applied to compositional modelling of diverse systems, including computational systems, logical systems, and physical systems, paving the way for a new kind of general system science (or rather general process science). It has been particularly successful in quantum computing and natural language processing recently; traditionally, it has played major rôles in compositional semantics of programming languages and symbolic reasoning systems. Building upon them, we propose the mathematical system of neural string diagrams as a universal modelling language for categorical deep learning, which allows us to turn informal neural network architecture pictures into formally explainable, mathematically verifiable, and systematically composable entities in their own right. We give, in particular, a neural string diagram account of CNN and Transformer (which has never been achieved before). Neural string diagrams can be computed with DisCoPy, Quantomatic, and their extensions. Categorically formalised neural networks can be instantiated for both ordinary vector spaces and other monoidal categorical structures, allowing for generalisations of deep learning (e.g., deep learning on relational structures, deep learning on graph and other network structures, etc.). We envisage that the category theory approach to artificial intelligence ultimately contributes to the development of artificial general intelligence, giving a universal modelling language for intelligent systems and agents.
This work was supported by JST (JPMJMS2033; JPMJPR17G9).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abramsky, S., Coecke, B.: Categorical quantum mechanics. In: Handbook of Quantum Logic and Quantum Structures, pp. 261–325 (2009)
Besold, T., et al.: Neural-Symbolic Learning and Reasoning (2017)
Clark, S., et al.: Mathematical foundations for a compositional distributional model of meaning. Linguist. Anal. 36, 345–384 (2010)
Coecke, B., Kissinger, A.: Picturing Quantum Processes. CUP (2017)
Cruttwell, G., et al.: Categorical foundations of gradient-based learning. arXiv arXiv:2103.01931 (2021)
De Felice, G., et al.: DisCoPy: monoidal categories in Python. In: 2020 Proceedings of the ACT, pp. 183–197 (2021)
Fong, B., Spivak, D.: An Invitation to Applied Category Theory. CUP (2019)
Goertzel, B., et al.: Guiding symbolic natural language grammar induction via transformer-based sequence probabilities. In: Proceedings of the AGI 2020, pp. 153–163 (2020)
Goertzel, B.: Human-level artificial general intelligence and the possibility of a technological singularity. Artif. Intell. 171, 1161–1173 (2007)
Grefenstette, E., Sadrzadeh, M.: Experimental support for a categorical compositional distributional model of meaning. In: Proceedings of the EMNLP, pp. 1394–1404 (2011)
Heunen, C., Vicary, J.: Categories for Quantum Theory. OUP (2019)
Lorenz, R., et al.: QNLP in practice. arXiv arXiv:2102.12846 (2021)
Maruyama, Y.: Categorical artificial intelligence: the integration of symbolic and statistical AI for verifiable, ethical, and trustworthy AI. In: Proceedings of the AGI (2021)
Sejnowski, T.: The unreasonable effectiveness of deep learning in artificial intelligence. PNAS 117, 30033–30038 (2020)
Zhang, Z., et al.: Deep learning on graphs. IEEE Trans. Knowl. Data Eng. 34, 249–270 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Xu, T., Maruyama, Y. (2022). Neural String Diagrams: A Universal Modelling Language for Categorical Deep Learning. In: Goertzel, B., Iklé, M., Potapov, A. (eds) Artificial General Intelligence. AGI 2021. Lecture Notes in Computer Science(), vol 13154. Springer, Cham. https://doi.org/10.1007/978-3-030-93758-4_32
Download citation
DOI: https://doi.org/10.1007/978-3-030-93758-4_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-93757-7
Online ISBN: 978-3-030-93758-4
eBook Packages: Computer ScienceComputer Science (R0)