Abstract
This chapter describes how the SP System, meaning the SP Theory of Intelligence, and its realisation as the SP Computer Model, may promote transparency and granularity in AI, and some other areas of application. The chapter describes how transparency in the workings and output of the SP Computer Model may be achieved via three routes: (1) the program provides a very full audit trail for such processes as recognition, reasoning, analysis of language, and so on. There is also an explicit audit trail for the unsupervised learning of new knowledge; (2) knowledge from the system is likely to be granular and easy for people to understand; and (3) there are seven principles for the organisation of knowledge which are central in the workings of the SP System and also very familiar to people (eg chunking-with-codes, part-whole hierarchies, and class-inclusion hierarchies), and that kind of familiarity in the way knowledge is structured by the system, is likely to be important in the interpretability, explainability, and transparency of that knowledge. Examples from the SP Computer Model are shown throughout the chapter.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
See, for example, Agisoft (www.agisoft.com/), All3DP (all3dp.com/), Sculpteo (www.sculpteo.com), and more.
References
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., and Fergus, R.: Intriguing properties of neural networks. Technical report, Google Inc. and others (2014). arXiv:1312.6199v4 [cs.CV] 19 Feb 2014, http://bit.ly/1elzRGM (PDF)
Nguyen, A., Yosinski, J., Clune, J.: Deep neural networks are easily fooled: high confidence predictions for unrecognizable images. In: Proceedings of the IEEE Confernce on Computer Vision and Pattern Recognition (CVPR 2015), pp. 427–436 (2015). https://doi.org/10.1109/CVPR.2015.7298640
Zadeh, L.A.: Toward a theory of fuzzy information granulation and its centrality in human reasoning and fuzzy logic. Fuzzy Sets Syst. 90, 111–127 (1997)
Pedrycz, W.: Granular computing for data analytics: a manifesto of human-centric computing. IEEE/CAA J. Automatica Sinica 5(6), 1025–1034 (2018)
Wolff, J.G.: The SP theory of intelligence: an overview. Information 4(3), 283–341 (2013). https://doi.org/10.3390/info4030283. arXiv:1306.3888 [cs.AI], http://bit.ly/1NOMJ6l
Wolff, J.G.: Unifying Computing and Cognition: The SP Theory and Its Applications. CognitionResearch.org, Menai Bridge (2006). ISBNs: 0-9550726-0-3 (ebook edition), 0-9550726-1-1 (print edition). Distributors, including Amazon.com, are detailed on http://bit.ly/WmB1rs
Kuhn, T.S.: The Structure of Scientific Revolutions. University of Chicago Press, Chicago and London, fourth, Kindle edition (2012)
Attneave, F.: Some informational aspects of visual perception. Psychol. Rev. 61, 183–193 (1954)
Barlow, H.B.: Sensory mechanisms, the reduction of redundancy, and intelligence. In: HMSO, editor, The Mechanisation of Thought Processes, pp. 535–559. Her Majesty’s Stationery Office, London (1959)
Barlow, H.B.: Trigger features, adaptation and economy of impulses. In: Leibovic, K.N. (ed.) Information Processes in the Nervous System, pp. 209–230. Springer, New York (1969)
Wolff, J.G.: Information compression as a unifying principle in human learning, perception, and cognition. Complexity 38 (2019). https://doi.org/10.1155/2019/1879746. Article ID 1879746. viXra:1707.0161v3, hal-01624595 v2
Wolff, J.G.: Information compression, multiple alignment, and the representation and processing of knowledge in the brain. Front. Psychol. 7, 1584 (2016). ISSN 1664-1078. https://doi.org/10.3389/fpsyg.2016.01584. arXiv:1604.05535 [cs.AI], http://bit.ly/2esmYyt
Wolff, J.G.: Mathematics as information compression via the matching and unification of patterns. Complexity 25 (2019). https://doi.org/10.1155/2019/6427493. Article ID 6427493, Archives: http://vixra.org/abs/1912.0100, http://hal.archives-ouvertes.fr/hal-02395680
Ford, M.: Architects of Intelligence: The Truth About AI From the People Building It. Packt Publishing, Birmingham, UK, Kindle edition (2018)
Wolff, J.G.: Problems in AI research and how the SP System may help to solve them (2020). Download: http://tinyurl.com/y48m84t5, submitted for publication
Wolff, J.G.: Big data and the SP Theory of Intelligence. IEEE Access 2, 301–315 (2014). https://doi.org/10.1109/ACCESS.2014.2315297. arXiv:1306.3890 [cs.DB], http://bit.ly/2qfSR3G. This paper, with minor revisions, is reproduced in Fei Hu (Ed.), Big Data: Storage, Sharing, and Security, Taylor & Francis LLC, CRC Press, 2016, Chapter 6, pp. 143–170
Wolff, J.G.: Application of the SP Theory of Intelligence to the understanding of natural vision and the development of computer vision. SpringerPlus 3(1), 552–570 (2014). https://doi.org/10.1186/2193-1801-3-552. arXiv:1303.2071 [cs.CV], http://bit.ly/2oIpZB6
Wolff, J.G.: Towards an intelligent database system founded on the SP theory of computing and cognition. Data Knowl. Eng. 60, 596–624 (2007). https://doi.org/10.1016/j.datak.2006.04.003. arXiv:cs/0311031 [cs.DB], http://bit.ly/1CUldR6
Wolff, J.G.: Medical diagnosis as pattern recognition in a framework of information compression by multiple alignment, unification and search. Decis. Support Syst. 42, 608–625 (2006). https://doi.org/10.1016/j.dss.2005.02.005. arXiv:1409.8053 [cs.AI], http://bit.ly/1F366o7
Palade, V., Wolff, J.G.: A roadmap for the development of the ‘SP Machine’ for artificial intelligence. The Comput. J. 62, 1584–1604 (2019). https://doi.org/10.1093/comjnl/bxy126. https://doi.org/10.1093/comjnl/bxy126 , arXiv:1707.00614, http://bit.ly/2tWb88M
Wolff, J.G.: Learning syntax and meanings through optimization and distributional analysis. In: Levy, Y., Schlesinger, I.M., Braine, M.D.S. (eds.) Categories and Processes in Language Acquisition, pp. 179–215. Lawrence Erlbaum, Hillsdale, NJ (1988). http://bit.ly/ZIGjyc
Lenneberg, E.H.: Understanding language without the ability to speak: a case report. J. Abnorm. Soc. Psychol. 65, 419–425 (1962)
Brown, C.: My Left Foot. Vintage Digital, London, Kindle edition (2014). First published in 1954
Chater, N., Vitányi, P.: ‘Ideal learning’ of natural language: positive results about learning from positive evidence. J. Math. Psychol. 51(3), 135–163 (2007). https://doi.org/10.1016/j.jmp.2006.10.002
Miller, G.A.: The magical number seven, plus or minus two: some limits on our capacity for processing information. Psychol. Rev. 63, 81–97 (1956)
Fujita, H., Gaeta, A., Loia, V., Orciuoli, F.: Resilience analysis of critical infrastructures: a cognitive approach based on granular computing. IEEE Trans. Cybern. 49(5), 1835–1848 (2018). https://doi.org/10.1109/TCYB.2018.2815178
Birtwistle, G.M., Dahl, O.-J., Myhrhaug, B., Nygaard, K.: Simula Begin. Studentlitteratur, Lund (1973)
Lee, S.-Y., Liou, R.-L.: A multi-granularity locking model for concurrency control in object-oriented database systems. IEEE Trans. Knowl. Data Eng. 8(1), 144–156 (1996)
Wolff, J.G.: Software engineering and the SP Theory of Intelligence. Technical report, CognitionResearch.org (2017). Submitted for publication. arXiv:1708.06665 [cs.SE], http://bit.ly/2w99Wzq
Zhang, Q., Zhu, S.-C.: Visual interpretability for deep learning: a survey. Front. Inf. Technol. Electron. Eng. 19, 27–39 (2018)
Alvarez-Melis, D., Jaakkola, T.S.: Towards robust interpretabilitywith self-explaining neural networks. In: Proceedings of the 32nd Conference on Neural Information Processing Systems (NeurIPS 2018). Montréal, Canada (2018)
Arrieta, A.B., Díaz-Rodríguez, N., Ser, J.D., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., Chatila, R., Herrera, F.: Explainable Artificial Intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI. Inf. Fusion 58, 82–115 (2020)
Byrne, R.M.J.: Counterfactuals in explainable artificial intelligence (XAI): evidence from human reasoning. In: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI-19, pp. 6276–6282 (2019)
Gunning, D., Stefik, M., Choi, J., Miller, T., Stumpf, S., Yang, G.-Z.: XAI—explainable artificial intelligence. Sci. Robot. 4(37), eaay7120 (2019). https://doi.org/10.1126/scirobotics.aay7120
Goebel, R., Chander, A., Holzinger, K., Lecue, F., Akata, Z., Stumpf, S., Kieseberg, P., Holzinger, A.: Explainable AI: The New 42? In: CD-MAKE 2018, 27-30 Aug 2018, Hamburg, Germany, Lecture Notes in Computer Science, volume 11015, pp. 295–303 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Wolff, J.G. (2021). Transparency and Granularity in the SP Theory of Intelligence and Its Realisation in the SP Computer Model. In: Pedrycz, W., Chen, SM. (eds) Interpretable Artificial Intelligence: A Perspective of Granular Computing. Studies in Computational Intelligence, vol 937. Springer, Cham. https://doi.org/10.1007/978-3-030-64949-4_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-64949-4_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-64948-7
Online ISBN: 978-3-030-64949-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)