Abstract
Memristive devices have attracted a large interest in the last few decades. The overall goal of this work is to propose a simulated analog computing platform that exploits memristors’ conductance programmability to implement a local learning algorithm for Dynamic Neural Networks: Equilibrium Propagation. During the training stage, the network oscillates between two phases in order to compute the gradient of an associated cost function. The weights update results in a Hebbian-like learning rule. Numerical simulations show that the method significantly outperforms conventional learning rules used for pattern reconstruction.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
LeCun Yann, Bengio Yoshua, Hinton Geoffrey (2015) Deep learning. Nature 521(7553):436
Xia Q, Joshua Yang J (2019) Memristive crossbar arrays for brain-inspired computing. Nat Mater 18(4):309–323
Burr GW, Shelby RM, Sebastian A, Kim S, Kim S, Sidler S, Virwani K, Ishii M, Narayanan P, Fumarola A et al (2017) Neuromorphic computing using non-volatile memory. Adv Phys X 2(1):89–124
Jeong YeonJoo, Wei Lu (2018) Neuromorphic computing using memristor crossbar networks: a focus on bio-inspired approaches. IEEE Nanotechnol Mag 12(3):6–18
Bengio Y, Lee D-H, Bornschein J, Mesnard T, Lin Z (2015) Towards biologically plausible deep learning. arXiv:1502.04156
Marblestone AH, Wayne G, Kording KP (2016) Toward an integration of deep learning and neuroscience. Front Comput Neurosci 10:94
Almeida LB (1987)A learning rule for asynchronous perceptrons with feedback in a combinatorial environment. In: Proceedings, 1st first international conference on neural networks, vol 2. IEEE, pp 609–618
Pineda FJ (1988) Generalization of back propagation to recurrent and higher order neural networks. In: Neural information processing systems, pp 602–611
Scellier Benjamin, Bengio Yoshua (2017) Equilibrium propagation: bridging the gap between energy-based models and backpropagation. Front Comput Neurosci 11:24
LeCun Y, Chopra S, Hadsell R, Ranzato M, Huang F (2006) A tutorial on energy-based learning. Predict Struct Data 1(0)
Mesnard T, Gerstner W, Brea J (2016) Towards deep learning with spiking neurons in energy based models with contrastive hebbian plasticity. arXiv:1612.03214
Chua LO, Mo Kang S (1976) Memristive devices and systems. Proc IEEE 64(2):209–223
Wang L, Yang C, Wen J, Gai S, Peng Y (2015) Overview of emerging memristor families from resistive memristor to spintronic memristor. J Mater Sci: Mater Electron 26:4618–4628
Petrenko S (2018) Limitations of von neumann architecture. In: Big data technologies for monitoring of computer security: a case study of the Russian federation. Springer, pp 115–173
Liu R, Mahalanabis D, Barnaby HJ, Yu S (2015) Investigation of single-bit and multiple-bit upsets in oxide rram-based 1t1r and crossbar memory arrays. IEEE Trans Nuclear Sci 62(5):2294–2301
Merced-Grafals EJ, Dávila N, Ge N, Stanley Williams R, Paul Strachan J (2016) Repeatable, accurate, and high speed multi-level programming of memristor 1t1r arrays for power efficient analog computing applications. Nanotechnology 27(36):365202
Storkey A (1997) Increasing the capacity of a hopfield network without sacrificing functionality. In: International conference on artificial neural networks. Springer, pp 451–456
Zoppo Gianluca, Marrone Francesco, Corinto Fernando (2020) Equilibrium propagation for memristor-based recurrent neural networks. Front Neurosci 14:240
Acknowledgements
This work has been supported by both the Ministero degli Affari Esteri e della Cooperazione Internazionale (MAECI) under the project n. PGR00823 and National Research Foundation of Korea (NRF) under the grant NRF-2019K1A3A1A25000279.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Zoppo, G., Marrone, F., Min, KS., Corinto, F. (2022). Energy-Based Memristor Networks for Pattern Recognition in Vision Systems. In: Chua, L.O., Tetzlaff, R., Slavova, A. (eds) Memristor Computing Systems. Springer, Cham. https://doi.org/10.1007/978-3-030-90582-8_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-90582-8_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-90581-1
Online ISBN: 978-3-030-90582-8
eBook Packages: EngineeringEngineering (R0)