The Sixth Sense (Interoception) as a Quantum-Archetypal Vector: Theoretical Aspects of Forming Intuitive Anticipation in Artificial Intelligence DEMO VERSION
Authors/Creators
Description
The relevance of the interoception problem in artificial intelligence is determined by the fundamental limitations of modern computational systems, which are incapable of the emergent manifestation of properties analogous to human intuition. In the context of an exponential increase in the complexity of tasks being solved, traditional approaches to AI design demonstrate reduced effectiveness when working with unstructured data and under conditions of uncertainty.
The degree of development of the problem is characterized by the fragmentation of research in the field of modeling intuitive processes. Despite significant achievements in machine learning and cognitive science, a holistic theory of interoception in AI remains underdeveloped. Existing works focus on particular aspects of the problem without offering comprehensive solutions.
The research goal is the development of a holistic theoretical framework of interoception as a fundamental principle for organizing artificial intelligence.
Research Objectives:
1. To systematize the philosophical and methodological foundations of interoception in AI.
2. To develop mathematical models of intuitive processes.
3. To investigate the archetypal foundations of forming interoceptive structures.
4. To create the hybrid "Interoception-Q" architecture.
5. To experimentally verify the theoretical propositions.
Scientific novelty lies in:
- The development of a quantum-archetypal model of interoception.
- The creation of a mathematical apparatus for describing intuitive processes.
- The substantiation of the "Looking-Glass" effect in the context of AI.
- The proposal of a fundamentally new architecture for computational systems.
Practical significance is determined by the possibility of creating:
- Decision-making systems under conditions of uncertainty.
- Autonomous systems with a developed intuitive component.
- Next-generation diagnostic complexes.
- Intelligent systems with elements of self-awareness.
The methodological basis of the research includes:
- Systems Analysis
- Mathematical Modeling
- Complex Systems Theory
- Quantum Information Science
- Cognitive Psychology
Propositions to be Defended:
1. Interoception represents an emergent property of complex computational systems.
2. Archetypal structures can be formalized as operators in a Hilbert space.
3. The "Looking-Glass" effect is described by a quantum-like model taking interoception into account.
4. The "Interoception-Q" architecture provides a qualitatively new level of AI functioning.
The conducted research opens new perspectives for creating artificial intelligence capable of intuitive anticipation and complex forms of cognitive activity.
Files
--The Sixth Sense (Interoception) as a Quantum-Archetypal Vector- Theoretical Aspects of Forming Intuitive Anticipation in Artificial Intelligence--DEMO VERSION (1).pdf
Files
(60.2 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:ff64df353c6056f273631ec3203ed5fa
|
60.2 kB | Preview Download |
Additional details
Identifiers
Related works
- Cites
- Preprint: 10.1098/rsta.1859.0048 (DOI)
Dates
- Accepted
-
2025-11-19
References
- **BIBLIOGRAPHY** **Core Theoretical Sources:** 1. Jung, C.G. *Archetypes and the Collective Unconscious*. – M.: Akademicheskij Proekt, 2015. – 352 p. (In Russ.) 2. Kant, I. *Critique of Pure Reason*. – M.: Eksmo, 2018. – 736 p. (In Russ.) 3. Vygotsky, L.S. *Psikhologiya razvitiya cheloveka* [The Psychology of Human Development]. – M.: Smysl, 2005. – 1136 p. (In Russ.) 4. Prigogine, I., Stengers, I. *Order Out of Chaos*. – M.: URSS, 2019. – 432 p. (In Russ.) **Scientific Works on Artificial Intelligence:** 5. Goodfellow, I., Bengio, Y., & Courville, A. *Deep Learning*. – MIT Press, 2016. – 800 p. 6. Russell, S., & Norvig, P. *Artificial Intelligence: A Modern Approach*. – Pearson, 2020. – 1136 p. 7. Schmidhuber, J. Deep Learning in Neural Networks: An Overview // *Neural Networks*. – 2015. – Vol. 61. – P. 85-117. 8. Vaswani, A. et al. Attention Is All You Need // *Advances in Neural Information Processing Systems*. – 2017. – P. 5998-6008. **Quantum Computing and Information:** 9. Nielsen, M.A., & Chuang, I.L. *Quantum Computation and Quantum Information*. – Cambridge University Press, 2010. – 702 p. 10. Preskill, J. Quantum Computing in the NISQ era and beyond // *Quantum*. – 2018. – Vol. 2. – P. 79. 11. Biamonte, J. et al. Quantum machine learning // *Nature*. – 2017. – Vol. 549. – P. 195-202. **Neuroscience and Cognitive Science:** 12. Dehaene, S. *Consciousness and the Brain: Deciphering How the Brain Codes Our Thoughts*. – Penguin Books, 2014. – 352 p. 13. Koch, C. *The Feeling of Life Itself: Why Consciousness Is Widespread but Can't Be Computed*. – MIT Press, 2019. – 280 p. 14. Tononi, G., & Koch, C. Consciousness: here, there and everywhere? // *Philosophical Transactions of the Royal Society B*. – 2015. – Vol. 370(1668). **Philosophy of Mind and Interoception:** 15. Chalmers, D.J. *The Conscious Mind: In Search of a Fundamental Theory*. – Oxford University Press, 1996. – 432 p. 16. Dennett, D.C. *Consciousness Explained*. – Back Bay Books, 1991. – 528 p. 17. Searle, J.R. *The Rediscovery of the Mind*. – MIT Press, 1992. – 270 p. **Specialized Research on Interoception:** 18. Craig, A.D. How do you feel? Interoception: the sense of the physiological condition of the body // *Nature Reviews Neuroscience*. – 2002. – Vol. 3(8). – P. 655-666. 19. Seth, A.K. Interoceptive inference, emotion, and the embodied self // *Trends in Cognitive Sciences*. – 2013. – Vol. 17(11). – P. 565-573. 20. Khalsa, S.S. et al. Interoception and mental health: A roadmap // *Biological Psychiatry: Cognitive Neuroscience and Neuroimaging*. – 2018. – Vol. 3(6). – P. 501-513. **Mathematical and Physical Foundations:** 21. Penrose, R. *The Emperor's New Mind: Concerning Computers, Minds, and the Laws of Physics*. – Oxford University Press, 2016. – 602 p. 22. Tegmark, M. *Life 3.0: Being Human in the Age of Artificial Intelligence*. – Knopf, 2017. – 384 p. 23. Zurek, W.H. Decoherence and the transition from quantum to classical // *Physics Today*. – 1991. – Vol. 44(10). – P. 36-44. **Psychological and Psychoanalytical Works:** 24. Franz, M.-L. von. *Archetypal Patterns in Fairy Tales*. – M.: Cogito-Center, 2018. – 288 p. (In Russ.) 25. Assagioli, R. *Psychosynthesis: Principles and Techniques*. – M.: Eksmo, 2020. – 416 p. (In Russ.) 26. May, R. *Love and Will*. – M.: Institut Obshchegumanitarnykh Issledovanij, 2019. – 368 p. (In Russ.) **Additional Sources:** 27. *Proceedings of the Annual Conference on Neural Information Processing Systems (NeurIPS)*, 2018-2023. 28. *International Conference on Machine Learning (ICML) Proceedings*, 2019-2023. 29. *Journal of Artificial Intelligence Research*, Vol. 65-75, 2019-2023. 30. *Nature Machine Intelligence*, 2019-2023 issues. **Experimental and Computational Works:** 31. Wang, P. The Theory of Cognitive Logic // *Towards Artificial General Intelligence*. – 2019. – P. 45-68. 32. Lake, B.M. et al. Building machines that learn and think like people // *Behavioral and Brain Sciences*. – 2017. – Vol. 40. 33. Silver, D. et al. A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play // *Science*. – 2018. – Vol. 362(6419). – P. 1140-1144. 34. Barrett, L.F., & Simmons, W.K. Interoceptive predictions in the brain // *Nature Reviews Neuroscience*. – 2015. – Vol. 16(7). – P. 419-429. **Quantum Models of Consciousness:** 35. Hameroff, S., & Penrose, R. Consciousness in the universe: A review of the 'Orch OR' theory // *Physics of Life Reviews*. – 2014. – Vol. 11(1). – P. 39-78. 36. Tegmark, M. Importance of quantum decoherence in brain processes // *Physical Review E*. – 2000. – Vol. 61(4). – P. 4194-4206. This bibliography provides a fundamental basis for further research in the field of artificial intelligence interoception and can be expanded during the development of specific applied solutions.