Research on Memristor-Based Neural Networks
DOI:
https://doi.org/10.62051/0ra1w557Keywords:
Memristor; Neural Networks; Optimization Algorithms; Low Power Consumption; Efficient Computing.Abstract
Memristors, a new kind of resistive device, have attracted considerable attention in recent years because of their nonvolatile nature, low energy consumption, and highly integrated performance. The key theory of the memristor is described, and its application in the structure of neural networks and arithmetic optimization is discussed. First, the fundamental models and operating properties of the memristor are evaluated, with emphasis on its voltage, current, and time variations. This paper reviews the performance of a variety of models based on the concept of memory, which can be used to reduce energy consumption and improve computation efficiency. Additionally, advancements in memristor technology that enhance the scalability and reliability of neural network architectures are explored. An optimal combination of pruning and quantizing is presented, which can greatly decrease the amount of data required by the neural network. Results show that the memristor has great potential to generate high performance, low power, and high efficiency in artificial intelligence applications, making it a promising component in the future of computing technology.
Downloads
References
[1] L. Chua, Memristor-The missing circuit element, IEEE Trans. Circuit Theory 18 (1971) 507-519.
[2] D. B. Strukov, G. S. Snider, D. R. Stewart, R. S. Williams, The missing memristor found, Nature 453 (2008) 80-83.
[3] S. P. Adhikari, M. P. Sah, H. Kim, L. O. Chua, Three fingerprints of memristor, IEEE Trans. Circuits Syst. I Reg. Papers 60 (2013) 3008-3021.
[4] Y. Zhang, X. Wang, E. G. Friedman, Memristor-Based Circuit Design for Multilayer Neural Networks, IEEE Trans. Circuits Syst. I Reg. Papers 65 (2018) 677-686.
[5] S. Kvatinsky, E. G. Friedman, A. Kolodny, U. C. Weiser, TEAM: Threshold adaptive memristor model, IEEE Trans. Circuits Syst. I Reg. Papers 60 (2013) 211-221.
[6] S. Kvatinsky, M. Ramadan, E. G. Friedman, A. Kolodny, VTEAM: A general model for voltage-controlled memristors, IEEE Trans. Circuits Syst. II Express Briefs 62 (2015) 786-790.
[7] Ascoli, F. Corinto, V. Senger, R. Tetzlaff, Memristor model comparison, IEEE Circuits Syst. Mag. 13 (2013) 89-105.
[8] Y. Zhang, X. Wang, Y. Li, E. G. Friedman, Memristive model for synaptic circuits, IEEE Trans. Circuits Syst. II Exp. Briefs 64 (2017) 767-771.
[9] Y. Li et al., Activity-dependent synaptic plasticity of a chalcogenide electronic synapse for neuromorphic systems, Sci. Rep. 4 (2014) 4906.
[10] D. Soudry, D. Di Castro, A. Gal, A. Kolodny, S. Kvatinsky, Memristor-Based Multilayer Neural Networks With Online Gradient Descent Training, IEEE Trans. Neural Netw. Learn. Syst. 26 (2015) 2408-2421.
[11] M. Guo, Y. Sun, Y. Zhu et al., Pruning and quantization algorithm with applications in memristor-based convolutional neural network, Cogn. Neurodyn. 18 (2024) 233-245.
[12] S. Dong, Y. Chen, Z. Fan, K. Chen, M. Qin, M. Zeng, X. Lu, G. Zhou, X. Gao, J.-M. Liu, A backpropagation with gradient accumulation algorithm capable of tolerating memristor non-idealities for training memristive neural networks, Neurocomputing 494 (2022) 89-103.
[13] S. Jin, S. Pei, Y. Wang, A variation tolerant scheme for memristor crossbar based neural network designs via two-phase weight mapping and memristor programming, Future Gener. Comput. Syst. 106 (2020) 270-276.
[14] R. Hasan, T. M. Taha, Enabling back propagation training of memristor crossbar neuromorphic processors, Proc. Int. Joint Conf. Neural Netw. (IJCNN), Jul. 2014, pp. 21-28.
[15] M. Hu et al., Memristor-based analog computation and neural network classification with a dot product engine, Adv. Mater. 30 (2018).
[16] Suresh et al., Realizing spike-timing dependent plasticity learning rule in Pt/Cu:ZnO/Nb: STO memristors for implementing single spike based denoising autoencoder, J. Micromech. Microeng. 29 (2019).
[17] Z. Wang, X. Wang, Z. Zeng, Memristive circuit design of brain-like emotional learning and generation, IEEE Trans. Cybern., Jul. 2021.
[18] Z. Liao, J. Fu, J. Wang, Ameliorate performance of memristor-based ANNs in edge computing, IEEE Trans. Comput. 70 (2021) 1299-1310.
[19] Z. Wang et al., Self-activation neural network based on self-selective memory device with rectified multilevel states, IEEE Trans. Electron Devices 67 (2020) 4166-4171.
Downloads
Published
Conference Proceedings Volume
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
