Abstract
The use of binary and multilevel memristors in the hardware neural networks implementation necessitates their weight coefficients quantization. In this paper we investigate the Hopfield network weights quantization influence on its information capacity and resistance to input data distortions. It is shown that, for a weight level number of the order of tens, the quantized weights Hopfield-Hebb network capacitance approximates its continuous weights version capacity. For a Hopfield projection network, similar result can be achieved only for a weight levels number of the order of hundreds. Experiments have shown that: (1) binary memristors should be used in Hopfield-Hebb networks, reduced by zeroing all weights in a given row which moduli are strictly less than the maximum weight in the row; (2) in the Hopfield projection networks with quantized weights, multilevel memristors with a weight levels number significantly more than two should be used, with a specific levels number depending on the stored reference vectors dimension, their particular set and the permissible input data noise level.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Haykin, S.: Neural Networks: A Comprehensive Foundation. Prentice Hall, Inc., Upper Saddle River (1999)
Hopfield, J.: Neural networks and physical systems with emergent collective computational abilities. Proc. Natl. Acad. Sci. USA 79, 2554–2558 (1982)
Personnaz, L., Guyon, I., Dreyfus, G.: Collective computational properties of neural networks: new learning mechanisms. Phys. Rev. A 34(5), 4217–4227 (1986)
Michel, A.N., Liu, D.: Qualitative Analysis and Synthesis of Recurrent Neural Networks. Marcel Dekker Inc., New York (2002)
Chua, L.: Memristor – the missing circuit element. IEEE Trans. Circuit Theory 18, 507–519 (1971)
Strukov, D.B., Snider, G.S., Stewart, D.R., Williams, R.S.: The missing memristor found. Nature 453, 80–83 (2008)
He, W., Sun, H., Zhou, Y., Lu, K., Xue, K., Miao, X.: Customized binary and multi-level HfO2 − x-based memristors tuned by oxidation conditions. Sci. Rep. 7, 10070 (2017)
Yu, S., Gao, B., Fang, Z., Yu, H., Kang, J., Wong, H.-S.P.: A low energy oxide-based electronic synaptic device for neuromorphic visual systems with tolerance to device variation. Adv. Mater. 25, 1774–1779 (2013)
Tarkov, M.S.: Crossbar-based hamming associative memory with binary memristors. In: Huang, T., Lv, J., Sun, C., Tuzikov, A.V. (eds.) ISNN 2018. LNCS, vol. 10878, pp. 380–387. Springer, Cham (2018). https://link.springer.com/chapter/10.1007/978-3-319-92537-0_44. Accessed 12 July 2018
Tarkov, M.S.: Synapses reduction in autoassociative Hopfield network. In: 2017 International Multi-conference on Engineering, Computer and Information Sciences (SIBIRCON). Novosibirsk, Russia, 18–22 September, pp. 158–160. IEEE (2017). https://ieeexplore.ieee.org/document/8109860/. Accessed 12 July 2018
Folli, V., Leonetti, M., Ruocco1, G.: On the maximum storage capacity of the Hopfield model. Front. Comput. Neurosci. 10, Article 144 (2017). https://www.frontiersin.org/articles/10.3389/fncom.2016.00144/full. Accessed 12 July 2018
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Tarkov, M.S. (2019). Hopfield Associative Memory with Quantized Weights. In: Kryzhanovsky, B., Dunin-Barkowski, W., Redko, V., Tiumentsev, Y. (eds) Advances in Neural Computation, Machine Learning, and Cognitive Research II. NEUROINFORMATICS 2018. Studies in Computational Intelligence, vol 799. Springer, Cham. https://doi.org/10.1007/978-3-030-01328-8_8
Download citation
DOI: https://doi.org/10.1007/978-3-030-01328-8_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-01327-1
Online ISBN: 978-3-030-01328-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)