Hybrid spiking-based multi-layered self-learning neuromorphic system based on memristor crossbar arrays
Abstract
Neuromorphic computing systems are under heavy investigation as a potential substitute for the traditional von Neumann systems in high-speed low-power applications. Recently, memristor crossbar arrays were utilized in realizing spiking-based neuromorphic system, where memristor conductance values correspond to synaptic weights. Most of these systems are composed of a single crossbar layer, in which system training is done off-chip, using computer based simulations, then the trained weights are pre-programmed to the memristor crossbar array. However, multi-layered, on-chip trained systems become crucial for handling massive amount of data and to overcome the resistance shift that occurs to memristors overtime. In this work, we propose a spiking-based multi-layered neuromorphic computing system capable of online training. The system performance is evaluated using three different datasets showing improved results versus previous work. In addition, studying the system accuracy versus memristor resistance shift shows promising results.
References
[1]
W. A. Wulf and S. A. McKee, "Hitting The Memory Wall: Implications of The Obvious," ACM SIGARCH Computer Architecture News, vol. 23, pp. 20--24, 1995.
[2]
C. Gamrat, "Challenges and Perspectives of Computer Architecture at the Nano Scale," in IEEE Comput. Soc. Annu. Symp. VLSI, 2010, pp. 8--10.
[3]
F. Akopyan et al., "Truenorth: Design and tool flow of a 65 mw 1 million neuron programmable neurosynaptic chip," IEEE Trans. Comput.-Aided Design Integr. Circuits Syst., vol. 34, pp. 1537--1557, 2015.
[4]
J. Schemmel, D. Briiderle, A. Griibl, M. Hock, K. Meier, and S. Millner, "A Wafer-Scale Neuromorphic Hardware System for Large-Scale Neural Modeling," in IEEE Int. Symp. Circuits and Syst. (ISCAS), 2010, pp. 1947--1950.
[5]
S. Mitra, S. Fusi, and G. Indiveri, "Real-Time Classification of Complex Patterns Using Spike-Based Learning in Neuromorphic VLSI," IEEE Trans. Biomed. Circuits Syst., vol. 3, pp. 32--42, 2009.
[6]
International Technology Roadmap of Semiconductors, 2013 Edition, Emerging Research Devices. {Online}. Available: http://www.itrs.net/
[7]
A. Thomas, "Memristor-Based Neural Networks," J. Physics D Appl. Physics, vol. 46, p. 093001, 2013.
[8]
S. H. Jo, T. Chang, I. Ebong, B. B. Bhadviya, P. Mazumder, and W. Lu, "Nanoscale Memristor Device as Synapse in Neuromorphic Systems," Nano letters, vol. 10, pp. 1297--1301, 2010.
[9]
T.-W. Lee and J. H. Nickel, "Memristor Resistance Modulation for Analog Applications," IEEE Electron Device Lett., vol. 33, pp. 1456--1458, 2012.
[10]
S. Yu, Y. Wu, and H.-S. P. Wong, "Investigating The Switching Dynamics and Multilevel Capability of Bipolar Metal Oxide Resistive Switching Memory," Appl. Physics Lett., vol. 98, p. 103514, 2011.
[11]
M. Hu, H. Li, Y. Chen, Q. Wu, G. S. Rose, and R. W. Linderman, "Memristor Crossbar-Based Neuromorphic Computing System: A Case Study," IEEE Trans. Neural Netw. Learn. Syst., vol. 25, pp. 1864--1878, 2014.
[12]
B. Li, Y. Wang, Y. Wang, Y. Chen, and H. Yang, "Training Itself: Mixed-Signal Training Acceleration for Memristor-Based Neural Network," in Asia and South Pacific Design Automation Conference (ASP-DAC), 2014, pp. 361--366.
[13]
R. Hasan and T. M. Taha, "Enabling Back Propagation Training of Memristor Crossbar Neuromorphic Processors," in Int. Joint Conf. Neural Networks (IJCNN), 2014, pp. 21--28.
[14]
S. B. Furber, F. Galluppi, S. Temple, and L. A. Plana, "The spinnaker project," Proc. IEEE, vol. 102, pp. 652--665, 2014.
[15]
C. Liu et al., "A Spiking Neuromorphic Design with Resistive Crossbar," in Design Automation Conference (DAC), 2015, pp. 14:1--14:6.
[16]
M. Chu et al., "Neuromorphic hardware system for visual pattern recognition with memristor array and cmos neuron," IEEE Trans. Ind. Electron., vol. 62, pp. 2410--2419, 2015.
[17]
A. M. Hassan, H. A. Fahmy, and N. H. Rafat, "Enhanced Model of Conductive Filament-Based Memristor via Including Trapezoidal Electron Tunneling Barrier Effect," IEEE Trans. Nanotechnol., vol. 15, pp. 484--491, 2016.
[18]
M. A. Zidan, A. M. Eltawil, F. Kurdahi, H. A. Fahmy, and K. N. Salama, "Memristor Multiport Readout: A Closed-Form Solution for Sneak Paths," IEEE Trans. Nanotechnol., vol. 13, pp. 274--282, 2014.
[19]
C. Liu and H. Li, "A Weighted Sensing Scheme for ReRAM-Based Cross-Point Memory Array," in IEEE Comput. Soc. Annu. Symp. VLSI, 2014, pp. 65--70.
[20]
B. Yan, A. M. Mahmoud, J. J. Yang, Q. Wu, Y. Chen, and H. H. Li, "A neuromorphic ASIC Design Using One-Selector-One-Memristor Crossbar," in IEEE Int. Symp. Circuits and Syst. (ISCAS), 2016, pp. 1390--1393.
[21]
C. Bishop, Pattern Recognition and Machine Learning. Springer, New York, 2001.
[22]
E. Zamanidoost, F. M. Bayat, D. Strukov, and I. Kataeva, "Manhattan Rule Training for Memristive Crossbar Circuit Pattern Classifiers," in IEEE Int. Symp. Intell. Signal Process. (WISP), 2015, pp. 1--6.
[23]
L. Prechelt, "PROBEN 1: A Set of Benchmarks and Benchmarking Rules for Neural Network Training Algorithms". Univ., Fak. für Informatik, 1994.
[24]
B. Liu et al., "Digital-Assisted Noise-Eliminating Training for Memristor Crossbar-Based Analog Neuromorphic Computing Engine," in Design Automation Conference (DAC), 2013, pp. 7:1--7:6.
- Hybrid spiking-based multi-layered self-learning neuromorphic system based on memristor crossbar arrays
Recommendations
Beyond spike-timing dependent plasticity in memristor crossbar arrays
2016 IEEE International Symposium on Circuits and Systems (ISCAS)Memristors have emerged as promising, area-efficient, nano-scale devices for implementing models of synaptic plasticity in hybrid CMOS-memristor neuromorphic architectures. These architectures aim at reproducing the learning capabilities of biological ...
Stochastic synaptic plasticity with memristor crossbar arrays
2016 IEEE International Symposium on Circuits and Systems (ISCAS)Memristive devices have been shown to exhibit slow and stochastic resistive switching behavior under low-voltage, low-current operating conditions. Here we explore such mechanisms to emulate stochastic plasticity in memristor crossbar synapse arrays. ...
On-chip training of memristor crossbar based multi-layer neural networks
Memristor crossbar arrays carry out multiply-add operations in parallel in the analog domain, and so can enable neuromorphic systems with high throughput at low energy and area consumption. On-chip training of these systems have the significant ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
March 2017
1814 pages
Publisher
European Design and Automation Association
Leuven, Belgium
Publication History
Published: 27 March 2017
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 80Total Downloads
- Downloads (Last 12 months)34
- Downloads (Last 6 weeks)14
Reflects downloads up to 12 Nov 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in