Skip to main content
Springer Nature Link
Log in

Metacognitive AI: Framework and the Case for a Neurosymbolic Approach

  • Conference paper
  • First Online:
Neural-Symbolic Learning and Reasoning (NeSy 2024)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 14980))

Included in the following conference series:

  • 520 Accesses

Abstract

Metacognition is the concept of reasoning about an agent’s own internal processes and was originally introduced in the field of developmental psychology. In this position paper, we examine the concept of applying metacognition to artificial intelligence. We introduce a framework for understanding metacognitive artificial intelligence (AI) that we call TRAP: transparency, reasoning, adaptation, and perception. We discuss each of these aspects in-turn and explore how neurosymbolic AI (NSAI) can be leveraged to address challenges of metacognition.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Making sense of raw input: Artif. Intell. 299, 103521 (2021)

    Article  Google Scholar 

  2. Abduljabbar, R., Dia, H., Liyanage, S., Bagloee, S.A.: Applications of artificial intelligence in transport: an overview. Sustainability 11(1), 189 (2019)

    Article  Google Scholar 

  3. Andrychowicz, M., et al.: Hindsight experience replay. Adv. Neural Inform. Process. Syst. 30 (2017)

    Google Scholar 

  4. Atkinson, E.: Man crushed to death by robot in south korea (Nov 2023). https://www.bbc.com/news/world-asia-67354709

  5. Badreddine, S., d’Avila Garcez, A., Serafini, L., Spranger, M.: Logic tensor networks. Artif. Intell. 303, 103649 (2022)

    Article  MathSciNet  Google Scholar 

  6. Caesar, H., et al.: nuscenes: a multimodal dataset for autonomous driving. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11621–11631 (2020)

    Google Scholar 

  7. Cornelio, C., Stuehmer, J., Hu, S.X., Hospedales, T.: Learning where and when to reason in neuro-symbolic inference. In: The Eleventh International Conference on Learning Representations (2022)

    Google Scholar 

  8. Cox, M.T.: Metacognition in computation: a selected history. In: AAAI Spring Symposium: Metacognition in Computation, pp. 1–17 (2005)

    Google Scholar 

  9. Cox, M.T., Raja, A.: Metareasoning: Thinking about thinking. MIT Press (2011)

    Google Scholar 

  10. Da, L., Mei, H., Sharma, R., Wei, H.: Uncertainty-aware grounded action transformation towards sim-to-real transfer for traffic signal control. In: 2023 62nd IEEE Conference on Decision and Control (CDC), pp. 1124–1129. IEEE (2023)

    Google Scholar 

  11. Dai, W.Z., Xu, Q., Yu, Y., Zhou, Z.H.: Bridging machine learning and logical reasoning by abductive learning. Adv. Neural Inform. Process. Syst. 32 (2019)

    Google Scholar 

  12. Dalal, A., Sarker, M.K., Barua, A., Hitzler, P.: Explaining deep learning hidden neuron activations using concept induction (2023)

    Google Scholar 

  13. Demetriou, A., Efklides, A., Platsidou, M., Campbell, R.L.: The architecture and dynamics of developing mind: Experiential structuralism as a frame for unifying cognitive developmental theories. Monographs of the society for research in child development, pp. i–202 (1993)

    Google Scholar 

  14. Du, L., Ding, X., Liu, T., Qin, B.: Learning event graph knowledge for abductive reasoning. In: Proc. of the 59th ACK. ACL (Aug 2021)

    Google Scholar 

  15. Evans, R., Grefenstette, E.: Learning explanatory rules from noisy data. J. Artifi. Intell. Res. 61, 1–64 (2018)

    Article  MathSciNet  Google Scholar 

  16. Farivar, C.: Cruise robotaxi dragged woman 20 feet in recent accident, local politician says (Oct 2023). https://www.forbes.com/sites/cyrusfarivar/2023/10/06/cruise-robotaxi-dragged-woman-20-feet-in-recent-accident-local-politician-says/?sh=2d68e761466b

  17. Flavell, J.H.: Metacognition and cognitive monitoring: a new area of cognitive-developmental inquiry. Am. Psychol. 34(10), 906 (1979)

    Article  Google Scholar 

  18. d’Avila Garcez, A., Lamb, L.C.: Neurosymbolic AI: the 3rd wave. CoRR (2020)

    Google Scholar 

  19. Giunchiglia, E., Lukasiewicz, T.: Coherent hierarchical multi-label classification networks. In: Proc. of the 34th International Conference of NIUPS, NIPS 2020, Red Hook, NY, USA (2020)

    Google Scholar 

  20. Grigorescu, S., Trasnea, B., Cocias, T., Macesanu, G.: A survey of deep learning techniques for autonomous driving. J. Field Robot. 37(3), 362–386 (2020)

    Article  Google Scholar 

  21. Hitzler, P., Sarker, M.K., Eberhart, A. (eds.): Compendium of Neurosymbolic Artificial Intelligence, Frontiers in Artificial Intelligence and Applications, vol. 369. IOS Press (2023)

    Google Scholar 

  22. Huang, Y.X., Dai, W.Z., Jiang, Y., Zhou, Z.H.: Enabling knowledge refinement upon new concepts in abductive learning (2023)

    Google Scholar 

  23. Izzo, D., Märtens, M., Pan, B.: A survey on artificial intelligence trends in spacecraft guidance dynamics and control. Astrodynamics 3, 287–299 (2019)

    Article  Google Scholar 

  24. Jayawardana, V., Tang, C., Li, S., Suo, D., Wu, C.: The impact of task underspecification in evaluating deep reinforcement learning. Adv. Neural. Inf. Process. Syst. 35, 23881–23893 (2022)

    Google Scholar 

  25. Kautz, H.A.: The third ai summer: Aaai robert s. engelmore memorial lecture. AI Mag. 43(1), 105–125 (2022)

    Google Scholar 

  26. Kim, J., Kim, J.H., Lee, G.: Gps data-based mobility mode inference model using long-term recurrent convolutional networks. Trans. Res. Part C: Emerging Technol. 135, 103523 (2022)

    Article  Google Scholar 

  27. Leibig, C., Allken, V., Ayhan, M.S., Berens, P., Wahl, S.: Leveraging uncertainty information from deep neural networks for disease detection. Sci. Rep. 7(1), 17816 (2017)

    Article  Google Scholar 

  28. Li, B.H., Hou, B.C., Yu, W.T., Lu, X.B., Yang, C.W.: Applications of artificial intelligence in intelligent manufacturing: a review. Front. Inform. Technol. Electronic Eng. 18, 86–96 (2017)

    Google Scholar 

  29. Mitsopoulos, K., Somers, S., Schooler, J., Lebiere, C., Pirolli, P., Thomson, R.: Toward a psychology of deep reinforcement learning agents using a cognitive architecture. Top. Cogn. Sci. 14(4), 756–779 (2022)

    Article  Google Scholar 

  30. Mok, A.: Chatgpt reportedly made up sexual harassment allegations against a prominent lawyer (Apil 2023). https://www.businessinsider.com/chatgpt-ai-made-up-sexual-harassment-allegations-jonathen-turley-report-2023-4#:~:text=OpenAI’s%20buzzy%20ChatGPT%20falsely%20accused,source%2C%20The%20Washington%20Post%20reported

  31. Shakarian, P., Baral, C., Simari, G.I., Xi, B., Pokala, L.: Neuro Symbolic Reasoning and Learning. Springer Briefs in Computer Science, Springer (2023)

    Google Scholar 

  32. Svenmarck, P., Luotsinen, L., Nilsson, M., Schubert, J.: Possibilities and challenges for artificial intelligence in military applications. In: Proceedings of the NATO Big Data and Artificial Intelligence for Military Decision Making Specialists’Meeting, pp. 1–16 (2018)

    Google Scholar 

  33. Ulam, P., Goel, A., Jones, J., Murdock, W.: Using model-based reflection to guide reinforcement learning. Reasoning, Represent. Learn. Comput. Games 107 (2005)

    Google Scholar 

  34. Wang, D., Yang, Q., Abdul, A., Lim, B.Y.: Designing theory-driven user-centric explainable ai. In: Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems, pp. 1–15 (2019)

    Google Scholar 

  35. Wei, H., et al.: Honor of kings arena: an environment for generalization in competitive reinforcement learning. Adv. Neural. Inf. Process. Syst. 35, 11881–11892 (2022)

    Google Scholar 

  36. Wei, H., Shakarian, P.: Metacognitive Artificial Intelligence. Cambridge University Press (2024)

    Google Scholar 

  37. Xi, B., Scaria, K., Shakarian, P.: Rule-based error detection and correction to operationalize movement trajectory classification (2023)

    Google Scholar 

  38. Xu, J., Zhang, Z., Friedman, T., Liang, Y., den Broeck, G.V.: A semantic loss function for deep learning with symbolic knowledge (2018)

    Google Scholar 

  39. Ye, K., Chen, T., Wei, H., Zhan, L.: Uncertainty regularized evidential regression. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38(15), pp. 16460–16468 (2024). https://doi.org/10.1609/aaai.v38i15.29583

Download references

Acknowledgement

This work was funded by the Army Research Office (ARO) under grants W911NF2310345 and W911NF2410007.

Author information

Authors and Affiliations

  1. Arizona State University, Tempe, USA

    Hua Wei & Paulo Shakarian

  2. Carnegie Mellon University, Pittsburgh, USA

    Christian Lebiere

  3. Colorado State University, Fort Collins, USA

    Bruce Draper & Nikhil Krishnaswamy

  4. Rensselaer Polytechnic Institute, Troy, USA

    Sergei Nirenburg

Authors
  1. Hua Wei
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Paulo Shakarian
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Christian Lebiere
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Bruce Draper
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Nikhil Krishnaswamy
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Sergei Nirenburg
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Paulo Shakarian .

Editor information

Editors and Affiliations

  1. Sony AI, Barcelona, Spain

    Tarek R. Besold

  2. City, University of London, London, UK

    Artur d’Avila Garcez

  3. City, University of London, London, UK

    Ernesto Jimenez-Ruiz

  4. University of Padova, Padova, Italy

    Roberto Confalonieri

  5. City, University of London, London, UK

    Pranava Madhyastha

  6. City, University of London, London, UK

    Benedikt Wagner

Ethics declarations

Disclosure of Interests

The authors have no competing interests.

Rights and permissions

Reprints and permissions

Copyright information

© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Wei, H., Shakarian, P., Lebiere, C., Draper, B., Krishnaswamy, N., Nirenburg, S. (2024). Metacognitive AI: Framework and the Case for a Neurosymbolic Approach. In: Besold, T.R., d’Avila Garcez, A., Jimenez-Ruiz, E., Confalonieri, R., Madhyastha, P., Wagner, B. (eds) Neural-Symbolic Learning and Reasoning. NeSy 2024. Lecture Notes in Computer Science(), vol 14980. Springer, Cham. https://doi.org/10.1007/978-3-031-71170-1_7

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-71170-1_7

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-71169-5

  • Online ISBN: 978-3-031-71170-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics