Abstract
The paper considers bidirectional associative memory, which is one of the known neural network paradigms. To simplify the implementation of the calculation of this paradigm, a discrete mathematical model of its functioning is proposed. Reducing the complexity is achieved by switching to integer calculations because Integer multiplication is several times simpler than real multiplication. The known neural network of bidirectional associative memory neural network was compared with the proposed one. The simulation was carried out in the VHDL language. For comparative evaluation, Spartan3E, Spartan6 and XC9500 chips were used. In the experimental part, it was shown that the hardware costs for the implementation of the neural network of bidirectional associative memory have decreased by more than 3 times compared to the known one. The proposed discrete model of BAM functioning does not narrow the scope of its application in comparison with the known model and can be used to build memory devices and restore distorted or noisy information.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Kosko, B.: Bidirectional associative memories. IEEE Trans. Syst. Man Cybern. 18(1), 49–60 (1988)
Cao, J.D., Wang, L.: Exponential stability and periodic oscillatory solution in BAM networks with delays. IEEE Trans. Neural Netw. 13(2), 457–463 (2002)
Sakthivel, R., et al.: Design of state estimator for bidirectional associative memory neural networks with leakage delays. Inf. Sci. 296, 263–274 (2015)
Xu, C.: Local and global Hopf bifurcation analysis on simplified bidirectional associative memory neural networks with multiple delays. Math. Comput. Simul. 149, 69–90 (2018)
Park, J.H., et al.: A new stability criterion for bidirectional associative memory neural networks of neutral-type. Appl. Math. Comput. 199(2), 716–722 (2008)
Shaposhnikov, A., Orazaev, A., Eremenko, E., Malakhov, D.: Hamming neural network in discrete form. In: Tchernykh, A., Alikhanov, A., Babenko, M., Samoylenko, I. (eds.) MANCS 2021. LNCS, vol. 424, pp. 11–17. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-97020-8_2
Ratnavelu, K., Manikandan, M., Balasubramaniam, P.: Synchronization of fuzzy bidirectional associative memory neural networks with various time delays. Appl. Math. Comput. 270, 582–605 (2015)
Aouiti, C., Sakthivel, R., Touati, F.: Global dissipativity of high-order hopfield bidirectional associative memory neural networks with mixed delays. Neural Comput. Appl. 32(14), 10183–10197 (2020)
Zhao, H.: Global stability of bidirectional associative memory neural networks with distributed delays. Phys. Lett. A 297(3–4), 182–190 (2002)
Cao, J., Liang, J., Lam, J.: Exponential stability of high-order bidirectional associative memory neural networks with time delays. Physica D 199(3–4), 425–436 (2004)
Kosko, B.: Adaptive bidirectional associative memories. Appl. Opt. 26(23), 4947–4960 (1987)
Aouiti, C., Sakthivel, R., Touati, F.: Global dissipativity of fuzzy bidirectional associative memory neural networks with proportional delays. Iranian J. Fuzzy Syst. 18(2), 65–80 (2021)
Humphries, U., et al.: Global stability analysis of fractional-order quaternion-valued bidirectional associative memory neural networks. Mathematics 8(5), 801 (2020)
Makhzani, A., Frey, B.J.: Winner-take-all autoencoders. Adv. Neural Information Processing Systems, vol. 28 (2015)
Ionisyan, A.S.: Investigation of FPGA utilization of continues and discrete bidirectional associative memory neural networks. https://github.com/anserion/bidirmem_VHDL. Accessed 16 June 2022
Acknowledgments
The authors would like to thank the North Caucasus Federal University for supporting the contest of projects competition of scientific groups and individual scientists of the North Caucasus Federal University. The work is supported by the North-Caucasus Center for Mathematical Research under agreement â„– 075-02-2021-1749 with the Ministry of Science and Higher Education of the Russian Federation and by Russian Foundation for Basic Research project 1907-00130.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Shaposhnikov, A.V., Ionisyan, A.S., Orazaev, A.R. (2023). Discrete Neural Network of Bidirectional Associative Memory. In: Alikhanov, A., Lyakhov, P., Samoylenko, I. (eds) Current Problems in Applied Mathematics and Computer Science and Systems. APAMCS 2022. Lecture Notes in Networks and Systems, vol 702. Springer, Cham. https://doi.org/10.1007/978-3-031-34127-4_32
Download citation
DOI: https://doi.org/10.1007/978-3-031-34127-4_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-34126-7
Online ISBN: 978-3-031-34127-4
eBook Packages: EngineeringEngineering (R0)