Abstract
This paper compares two neural network learning schemes in crossbar architecture, using memristive elements. Novel memristive crossbar architecture with dense synaptic connections suitable for online training was developed. Training algorithms and simulations of the two proposed learning schemes, winner adjustment training (WAT) and multiple adjustments training (MAT) are presented. Tests performed using MNIST handwritten character recognition benchmark dataset confirmed the functionality of proposed learning schemes. Proposed learning schemes were compared accounting for noise, device variations and multipath effects. The proposed learning schemes improve available neural network learning schemes.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Chua, L.: Memristor-the missing circuit element. IEEE Trans. Circuit Theory CT-18(5), 507–519 (1971)
Strukov, D.B., Snider, G.S., Stewart, D.R., Williams, R.S.: The missing memristor found. Nature 453, 80–83 (2008)
Pershin, Y.V., Di Ventra, M.: Experimental demonstration of associative memory with memristive neural networks. Neural Netw. 23(7), 881–886 (2010)
Pershin, Y.V., Di Ventra, M.: Solving mazes with memristors: A massively parallel approach. Phys. Rev. EÂ 84(4), 046703 (2011)
Cantley, K.D., Subramaniam, A., Stiegler, H., Chapman, R., Vogel, E.: Neural learning circuits utilizing nano-crystalline silicon transistors and memristors. IEEE Trans. Neural Networks Learning Syst. 23(4), 565–573 (2012)
Kim, H., Sah, M.P., Yang, C., Roska, T., Chua, L.O.: Memristor Bridge Synapses. Proceedings of the IEEE 100(6), 2061–2070 (2012)
Chang, T., Jo, S.-H., Kim, K.-H., Sheridan, P., Gaba, S., Lu, W.: Synaptic behaviors and modeling of a metal oxide memristive device. Appl. Phys. A 102(4), 857–863 (2011)
Liu, L., Chen, B., Gao, B., Zhang, F., Chen, Y., Liu, X., Wang, Y., Han, R., Kang, J.: Engineering oxide resistive switching materials for memristivedevice application. Appl. Phys. A 102(4), 991–996 (2011)
Jo, S.H., Chang, T., Ebong, I., Bhadviya, B.B., Mazumder, P., Lu, W.: Nanoscale memristor device as synapse in neuromorphic systems. Nano Lett. 10(4), 1297–1301 (2010)
Chabi, D., Klein, J.-O.: Hight fault tolerance in neural crossbar. In: 2010 5th International Conference on Design and Technology of Integrated Systems in Nanoscale Era (DTIS), March 23-25, pp. 1–6 (2010)
Querlioz, D., Zhao, W.S., Dollfus, P., Klein, J.-O., Bichler, O., Gamrat, C.: Bioinspired networks with nanoscale memristive devices that combine the unsupervised and supervised learning approaches. In: 2012 IEEE/ACM International Symposium on Nanoscale Architectures (NANOARCH), July 4-6, pp. 203–210 (2012)
Strukov, D.B., Borghetti, J.L., Williams, R.S.: Coupled ionic and electronic transport model of thin-film semiconductor memristive behavior. Small 5(9), 1058–1063 (2009)
Pickett, M., Strukov, D.B., Borghetti, J., Yang, J., Snider, G., Stewart, D., Williams, R.S.: Switching dynamics in a titanium dioxide memristive device. J. of App. Phys. 106, art. 074508 (2009)
The MNIST database of handwritten digits, http://yann.lecun.com/exdb/mnist/
Gray, D.T.: Optimization of the Process for Semiconductor Device Fabrication in the MicrON 636 Whittemore Cleanroom Facility. M.S. thesis, Materials Sc. Eng., Virginia Polytechnic Inst. and State Uni., Blacksburg, VA (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Starzyk, J.A., Basawaraj (2013). Comparison of Two Memristor Based Neural Network Learning Schemes for Crossbar Architecture. In: Rojas, I., Joya, G., Gabestany, J. (eds) Advances in Computational Intelligence. IWANN 2013. Lecture Notes in Computer Science, vol 7902. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-38679-4_49
Download citation
DOI: https://doi.org/10.1007/978-3-642-38679-4_49
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-38678-7
Online ISBN: 978-3-642-38679-4
eBook Packages: Computer ScienceComputer Science (R0)