Advertisement

Emergence of Belief Systems and the Future of Artificial Intelligence

  • Howard SchneiderEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 948)

Abstract

In the Meaningful-Based Cognitive Architecture (MBCA), every evaluation cycle the input sensory vector is propagated through a hierarchy of Hopfield-like Network (HLN) functional groups, and subsymbolic processing of the input vector occurs. The processed sensory input vector is also propagated to causal groups of HLNs and/or logic/working memory groups of HLNs, where it is matched against the vector from the MBCA’s intuitive and learned logic, physics, psychology and goal planning—collectively forming its world model or belief system. The output of the logic/working memory can be propagated back to the start of the subsymbolic system where it can be the input for the next evaluation cycle, and allows multiple symbolic processing steps to occur on intermediate results. In this fashion, full symbolic causal processing of the input sensory vector occurs. In order to achieve causal and symbolic processing of sensory input, i.e., allowing the MBCA to not only recognize but interpret events in the environment and produce motor outputs in anticipation of future outcomes, every evaluation cycle the MBCA must not simply process the input sensory vector for subsymbolic recognition, but must process this vector in terms of the belief system activated. Artificial Neural Networks have excellent pattern recognition and reinforcement learning abilities, but perform poorly at causally and logically making sense of their environment. Future artificial intelligence systems that attempt to overcome the limitations of subsymbolic architectures by the integration of symbolic processing, may be at risk for developing faulty belief systems with unintended results.

Keywords

Cognitive architecture Artificial general intelligence Cortical minicolumns Belief systems Neural-symbolic integration 

Notes

Acknowledgments

Thanks for discussion to Dr. Aliye Keskin. This article builds upon work originally presented at BICA 2018 (reference 5).

References

  1. 1.
    Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT Press, CambridgezbMATHGoogle Scholar
  2. 2.
    Mnih V, Kavukcuoglu K, Silver D et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529–533CrossRefGoogle Scholar
  3. 3.
    Ullman S (2019) Using neuroscience to develop artificial intelligence. Science 363(6428):692–693CrossRefGoogle Scholar
  4. 4.
    Waismeyer A, Meltzoff AN, Gopnik A (2015) Causal learning from probabilistic events in 24-month-olds: an action measure. Dev Sci 18(1):175–182CrossRefGoogle Scholar
  5. 5.
    Schneider H (2018) Meaningful-based cognitive architecture. Procedia Comput Sci 145:471–480 BICA 2018, ed Samsonovich, A.V.CrossRefGoogle Scholar
  6. 6.
    Schneider H (2019, in press) Subsymbolic versus Symbolic data flow in the meaningful-based cognitive architecture. In: Samsonovich AV (ed) Biologically inspired cognitive architectures 2019, BICA 2019. Advances in intelligent systems and computing. SpringerGoogle Scholar
  7. 7.
    Schneider H (2019, in press) Schizophrenia and the future of artificial intelligence. In: Samsonovich AV (ed) Biologically inspired cognitive architectures 2019, BICA 2019. Advances in intelligent systems and computing. SpringerGoogle Scholar
  8. 8.
    Samsonovich AV (2010) Toward a unified catalog of implemented cognitive architectures. In: BICA, vol 221, pp 195–244Google Scholar
  9. 9.
    Bach J (2008) Seven principles of synthetic intelligence. In: Proceedings of 1st conference on artificial general intelligence, Memphis, pp 63–74Google Scholar
  10. 10.
    Rosenbloom P, Demski A, Ustun V (2016) The sigma cognitive architecture and system: towards functionally elegant grand unification. J Artif Gen Intell 7(1):1–103CrossRefGoogle Scholar
  11. 11.
    Collier M, Beel J (2018) Implementing neural Turing machines. In: ICANNGoogle Scholar
  12. 12.
    Mountcastle VB (1997) Columnar organization of the neocortex. Brain 20:701–722CrossRefGoogle Scholar
  13. 13.
    Buxhoeveden DP, Casanova MF (2002) The minicolumn hypothesis in neuroscience. Brain 125(Pt 5):935–951CrossRefGoogle Scholar
  14. 14.
    Schwalger T, Deger M, Gerstner W (2017) Towards a theory of cortical columns. PLoS Comput Biol 13(4): e1005507.  https://doi.org/10.1371/journal.pcbi.1005507 CrossRefGoogle Scholar
  15. 15.
    Eliasmith C, Trujillo O (2014) The use and abuse of large-scale brain models. Curr Opin Neurobiol 25:1–6CrossRefGoogle Scholar
  16. 16.
    Nissani M (2006) Do Asian elephants (Elaphas maximus) apply causal reasoning to tool-use tasks? J Exp Psychol Anim Behav Process 32(1):91–96CrossRefGoogle Scholar
  17. 17.
    Sawa K (2009) Predictive behavior and causal learning in animals and humans. Jpn Psychol Res 51(3):222–233CrossRefGoogle Scholar
  18. 18.
    Laumer IB, Bugnyar T, Reber SA, Auersperg A (2017) Can hook-bending be let off the hook? Bending/unbending of pliant tools by cockatoos. Proc Biol Sci 284(1862). 20171026CrossRefGoogle Scholar
  19. 19.
    Bostrom N (2014) Superintelligence: paths, dangers, strategies. Oxford University Press, OxfordGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Sheppard Clinic NorthTorontoCanada

Personalised recommendations