Mechanism for forming internal correlation when concepts are generated on a neural network with connections produced by Fourier holography

Vasiliev, V.N., Isakov, K.A., Lyalyushkin, S.S., Pavlov, A.V.

Publication in Journal of Optical Technology

For Russian citation (Opticheskii Zhurnal):

Васильев В.Н., Исаков К.А., Лялюшкин Л.С., Павлов А.В. Механизм формирования внутренней коррелированности при порождении понятий на нейросети со связями по схеме голографии фурье // Оптический журнал. 2013. Т. 80. № 10. С. 44–52.

Vasil’ev, V. N.; Isakov, K. A.; Lyalyushkin, L. S.; Pavlov, A. V. Mechanism for forming internal correlation when concepts are generated on a neural network with connections produced by Fourier holography [in Russian] // Opticheskii Zhurnal. 2013. V. 80. № 10. P. 44–52.

For citation (Journal of Optical Technology):

V. N. Vasil’ev, K. A. Isakov, L. S. Lyalyushkin, and A. V. Pavlov, "Mechanism for forming internal correlation when concepts are generated on a neural network with connections produced by Fourier holography," Journal of Optical Technology. 80(10), 616-622 (2013). https://doi.org/10.1364/JOT.80.000616

Abstract:

The interaction of two competing mechanisms that participate in the formation of a concept is considered in developing an approach to the implementation of inductive generalization in a Fourier-holography setup as a method of generating abstract concepts on the basis of sensory-pattern processing. These mechanisms are nonlinear iterative mapping in the correlation plane, which breaks down the internal correlation of the concept, and diffraction on a rerecorded hologram, which restores the internal correlation. It is shown that the characteristics of the index (reference) pattern that represents reality and the characteristics of the hologram, determined by the properties of the recording medium and by the method of recording it, have an effect on the formation of the internal correlation of the generated concept that prevails over the characteristics of the iterative mapping.

Keywords:

holography, information, internal correlation, cognitive systems, artificial intelligence, figurative thinking, concept, inductive generalization, neural networks

References:

1O. P. Kuznetsov, “Cognitive semantics and artificial intelligence,” Iskusst. Intellekt Prinyat. Reshen. No. 4, 32 (2012).
2G. A. Golitsyn and I. B. Fominykh, “Neural networks and expert systems: prospects of integration,” Novosti Iskusst. Intellekta No. 4, 121 (1996).
3V. P. Leutin and E. I. Nikolaeva, Functional Asymmetry of the Brain. Myths and Reality (Rech’, St. Petersburg, 2005).
4O. P. Kuznetsov, “Nonclassical paradigms in AI,” Izv. Akad. Nauk. Ser.: Teor. Sis. Upravleniya No. 5, 3 (1995).
5N. B. Tushkanov and O. N. Tushkanova, “Constructing multisensor systems: operating principles of the neocortex of the brain when recognizing
objects of the external world,” in Transactions of the Congress on Intelligent Systems and Information Technologies, IS-IT’12 (FIZMATLIT, Moscow, 2012), Vol. 2, pp. 373–378.
6S. P. Springer and G. Deutsch, Left Brain, Right Brain: Perspectives from Cognitive Neuroscience (W. H. Freeman, New York, 2001; Mir, Moscow,
1983).
7O. P. Kuznetsov, A. V. Markovskıı˘, and L. B. Shipilina, Holographic Mechanisms for Processing Pattern Information (Inst. Problem Upravleniya, Moscow, 2007).
8V. N. Vagin, E. Yu. Golovina, A. A. Zagoryanskaya, and M. V. Fomina, The Reliability and Probability Approach in Intelligent Systems (FIZMATLIT, Moscow, 2008).
9A. B. Barskiı˘, Logical Neural Networks (Binom, Moscow, 2007).
10A. V. Pavlov, “The possibility of implementing plausible reasoning by means of Fourier holography,” Opt. Zh. 77, No. 5, 24 (2010) [J. Opt. Technol. 77, 316 (2010)].
11A. V. Pavlov, “On stipulating the characteristics of a concept during its inductive formation on neural networks with connections according to a Fourier-holography setup,” in Seventh International Scientific-Practical Conference on Integrated Models and Soft Computations in Artificial Intelligence. Collection of Scientific Papers (FIZMATLIT, Moscow, 2011), Vol. 1, pp. 349–359.
12V. I. Korogodin, Information and the Phenomenon of Life (Akad. Nauk SSSR, Pushchino, 1991).
13Yu. L. Klimontovich, Introduction to the Physics of Open Systems (Yanus-K, Moscow, 2002).
14D. S. Chernavskiı˘, Synergetics and Information. A Dynamic Theory of Information (URSS, Moscow, 2009).
15I. R. Prigogine and I. Stengers, Das Paradox der Zeit. Zeit, Chaos und Quanten (Piper, 1993; KomKniga, Moscow, 2005).
16A. V. Pavlov, “Concerning the stipulation of the characteristics of the concept formed by a neural network with connections in Fourier space,” in Twelfth National Conference on Artificial Intelligence. Transactions of the Conference (Izd. BGTU, Belgorod, 2012), Vol. 1, pp. 358–366.
17Z. S. Bekyasheva, V. N. Vasil’ev, and A. V. Pavlov, “Models of the advancement of hypotheses in a Fourier-holography layout,” Opt. Zh. 80, No. 3, 37 (2013) [J. Opt. Technol. 80, 154 (2013)].
18G. A. Carpenter and S. Grossberg, “ART 2: self-organization of stable category-recognition codes for analog input patterns,” Appl. Opt. 26, 4919 (1987).
19E. I. Shubnikov, “Signal-to-noise ratio in correlation comparison of images,” Opt. Spektrosk. 62, 450 (1987) [Opt. Spectrosc. (USSR) 62, 268 (1987)].
20R. M. Kronover, Fractals and Chaos in Dynamic Systems (Postmarket, Moscow, 2000).
21N. A. Magnitskıı˘, “Pattern recognition by distributed dynamic systems,” Doklady Rossiiskoi akademii selskokhoziaistvennykh nauk 338, 320 (1994) [Phys.–Dokl. 39, 623 (1994)].
22A. M. Kuleshov, E. I. Shubnikov, and S. A. Smaeva, “On the optimal nature of a holographic matched filter,” Opt. Spektrosk. 60, 1273 (1986) [Opt.
Spectrosc. (USSR) 60, 791 (1986)].
23O. D. Chernavskaya, D. S. Chernavskiı˘, and A. P. Nikitin, On a Possible Mechanism of “Intuitive” and “Logical” in Neural Computing (FIAN,
Moscow, 2009).
24I. B. Fominykh, “On the technology of solving creative problems,” in Collected Transactions of the Eighth National Conference on Artificial
Intelligence, KII-2002 (FIZMATLIT, Moscow, 2002), Vol. 1, pp. 519–526