Development of an imagery representation apparatus for information representation in neyromorphic devices

Cover Page

Cite item

Full Text

Open Access Open Access
Restricted Access Access granted
Restricted Access Subscription Access

Abstract

The paper considers the application of the mathematical apparatus of spots for neuromorphic devices on crossbars of memory elements, the architecture of which corresponds to the technique of computing in memory. The apparatus of spots allows to represent and process semantic information in the form of mental imagery, as well as to model reasoning in a form inherent to a person. In particular, these are deductive, inductive, abductive, as well as non-monotonic reasoning, when conclusions are made on the basis of existing knowledge, and obtaining new knowledge can change the conclusions. The apparatus of spots is the mathematical basis for creating neuromorphic devices with the technique of computing in memory, capable of not only representing semantic information in an imaginary form, but also modeling imaginative thinking. This will solve a major problem for modern deep neural networks associated with the possibility of random, causeless errors.

Full Text

Restricted Access

About the authors

N. А. Simonov

Valiev Institute of Physics and Technology, Russian Academy of Sciences

Author for correspondence.
Email: nsimonov@ftian.ru
Russian Federation, Moscow

References

  1. Seo J.S., Brezzo B., Liu Y., Parker B.D., et al. A 45nm CMOS neuromorphic chip with a scalable architecture for learning in networks of spiking neurons // IEEE Custom Integrated Circuits Conf (CICC). 2011. P. 1–4. IEEE.
  2. Indiveri G., Linares-Barranco B., Hamilton T.J. et al. Neuromorphic silicon neuron circuits // Front. Neurosci. 2011. V. 5. P. 1–23.
  3. Zhu J., Zhang T., Yang Y., and Huang R. A comprehensive review on emerging artificial neuromorphic devices // Applied Physics Reviews. 2020. Rev. 7, 011312. P. 1–107.
  4. Gostev A.A. Psychology of the Secondary Image. M.: Litres. 2022 (in Russian).
  5. Gorban A.N. The Problem of Reliability of Multidimensional AI in a Multidimensional World. Presentation at the ONIT RAS Meeting, February 24 2022. URL: https://cloud.niime.ru/s/fwfX8eYHg6EDz6q?path=%2F2021%20-%202023 (in Russian).
  6. Image Classification on ImageNet. URL: https://paperswithcode.com/sota/image-classification-on-imagenet
  7. Searle J.R. Minds, brains, and programs // Behav. Brain Sci. 1980. V. 3. P. 417–424.
  8. Finn V.K. Inductive methods of D.S. Mill in artificial intelligence systems. Part I // Artificial intelligence and decision making. 2010. № 3. С. 3–21 (in Russian).
  9. Finn V.K. Inductive methods of D.S. Mill in artificial intelligence systems. Part II // Artificial intelligence and decision making. 2010. № 4. С. 14–40.
  10. Wang P. Cognitive Logic vs Mathematical Logic // Lecture Notes of the 3rd International Seminar on Logic and Cognition. China, Guangzhou, 2004.
  11. Hadamard J. An essay on the psychology of invention in the mathematical field. Courier Corporation. 1954.
  12. Simonov N.A. Spots Concept for Problems of Artificial Intelligence and Algorithms of Neuromorphic Systems // Russian Microelectronics. 2020. V. 49. P. 431–444. https://doi.org/10.1134/S106373972005008X
  13. Simonov N.A. Application of the model of spots for inverse problems. // Sensors. 2023. V. 23. No 3. 1247.
  14. Simonov N.A., Rusalova M.N. Mental imagery representation by model of spots in psychology // Natural Systems of Mind. 2023. V. 3. No 1. P. 4–22.
  15. Nanay B. Mental Imagery // E.N. Zalta (ed.) The Stanford Encyclopedia of Philosophy. 2021. [Электронный ресурс] URL: https://plato.stanford.edu/archives/win2021/entries/mental-imagery/
  16. Vekker L.M. Psyche and reality: a unified theory of mental processes. M.: Smysl, 1998 (in Russian).
  17. Simonov N.A. Spatial representation of concepts and processes in psychology by the spots model // Natural Systems of Mind. 2024. V. 4. No 2, P. 6–20. https://doi.org/ 10.38098/nsom_2024_04_02_01.
  18. Sima J.F., Freksa C. Towards computational cognitive modeling of mental imagery: The attention-based quantification theory // KI-Künstliche Intelligenz. 2012. V. 26. P. 261–267.
  19. Donini F.M., Lenzerini M., Nardi D., Pirri F., and Schaerf M. Nonmonotonic reasoning // Artificial Intelligence Review. 1990. V. 4. No 3. P. 163–210.
  20. Svetlov V.A. Charles Peirce's Methodological Concept of Scientific Knowledge: The Unity of Abduction, Deduction and Induction // Logiko-fylosofskiye shtudii. 2012. No 5. P. 165–188 (in Russian).
  21. Bochman A. Causal reasoning from almost first principles // Synthese. 2024. V. 203:19.
  22. Wikipedia contributors, 'Karnaugh map' // Wikipedia, The Free Encyclopedia, 20 August 2024, from https://en.wikipedia.org/w/index.php?title=Karnaugh_map&oldid=1241369572.
  23. Simonov N.A. Development of a mathematical apparatus with an imagery representation of information for neuromorphic systems. // Russian Microelectronics. 2023. V. 52. No 6, Suppl. 1. P. S158–S161.
  24. Ielmini D. and Wong H.S.P. In-memory computing with resistive switching devices // Nature electronics. 2018. V.1. No 6. P. 333–343.
  25. Tarkov M., Tikhonenko F., Popov V., Antonov V., Miakonkikh A., and Rudenko K. Ferroelectric Devices for Content-Addressable Memory. Nanomaterials. 2022. V. 12. 4488.
  26. Akers S.B. A rectangular logic array // 12th Annual Symposium on Switching and Automata Theory (SWAT). 1971. P. 79–90. IEEE.
  27. Levy Y., Bruck J., Cassuto Y., Friedman E.G., Kolodny A., Yaakobi E., and Kvatinsky S. Logic operations in memory using a memristive Akers array // Microelectronics Journal. 2014. V. 45. No 11. P. 1429–1437.
  28. Borghetti J., Snider G.S., Kuekes P.J., Yang J.J., Stewart D.R., and Williams R.S. Memristive’switches enable ‘stateful’logic operations via material implication // Nature. 2010. V. 464. P. 873–876.
  29. Kvatinsky S., Belousov D., Liman S., Satat G., Wald N., Friedman E.G., Kolodny A. and Weiser U.C. MAGIC – Memristor-aided logic // IEEE Transactions on Circuits and Systems II: Express Briefs. 2014. V. 61. No 11. P. 895–899.
  30. Gupta S., Imani M. and Rosing T. Felix: Fast and energy-efficient logic in memory // IEEE/ACM International Conference on Computer-Aided Design (ICCAD). 2018. P. 1–7. IEEE.
  31. Udovichenko S., Pisarev A., Busygin A., Mayevskiy O. 3D CMOS memristor nanotechnology for creating logical and memory matrices of a neuroprocessor // Nanoindustry. 2017. No 5. P. 26–34 (in Russian).
  32. Udovichenko S., Pisarev A., Busygin A., Mayevskiy O. Neuroprocessor based on a combined memristor-diode crossbar // Nanoindustry. 2018. V. 11. No 5. P. 344–355 (in Russian).

Supplementary files

Supplementary Files
Action
1. JATS XML
Download
2. Formula 27

Download (37KB)
Indexing metadata
3. Fig. 2. Euler-Venn diagram for intersections of spots, illustrating the geometric meaning of the introduced L4 numbers for the EOE between two spots: (a) intersection of spots a and b; (b) separateness of spots a and b; (c) inclusion of b in a; (d) inclusion of a in b.

Download (229KB)
Indexing metadata
4. Fig. 3. An example of reconstruction of a poorly structured image of a star: (a) an image of a star in the form of randomly located points inside its contour; (b) reconstruction of the shape of a star based on the EPO data of image (a) with a scanning circle, shown in figure (b), with a small period.

Download (178KB)
Indexing metadata
5. Fig. 4. An example of the architecture of one layer of figurative-logical neural networks: (a) modeling of generalization or synthesis; (b) modeling of analysis.

Download (195KB)
Indexing metadata

Copyright (c) 2024 Russian Academy of Sciences