Abstract
Recently, neural networks have been developed for variable purposes including image and voice recognitions. However, those based on only software implementation require huge amount of calculation and energy. Therefore, we are now designing a hardware with cellular neural network (CNN) that features low power, high-density, and high-functionality. In this study, we developed a CNN simulator for evaluating some letter reproduction algorithm. In this simulator, each of the neurons is just connected to neighboring neurons with surrounding synapses. Learning process is executed by modifying the strength of each connection. Particularly, we assumed to employ a-IGZO films for crosspoint-type synapses that utilize a phenomenon that the conductance changes when an electric current flows. We modeled this phenomenon and implemented it into the simulator to determine the network architecture and device parameters. In this paper, the structure, allocation method of a-IGZO and the algorithm are described. Finally, we confirmed that our cellular neural network can learn two letters. Furthermore, it was found that the estimated time for learning is around 100 h based on the current characteristic change model of a-IGZO film, and some conditions to enhance the deterioration speed of a-IGZO film should be explored.
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
Dayhoff, J.E.: Neural Network Architectures, An Introduction. Van Nostrand Reinhold, New York (1990)
Mountcastle, V.B.: The Cerebral Cortex. Harvard University Press, Cambridge and London (1998)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278–2324 (1998)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS 2012 (2012)
Mead, C.: Analog VLSI and Neural Systems. Addison-Wesley Publishing, Boston (1989)
Prezioso, M.: Training and operation of an integrated neuromorphic network based on metal-oxide memristors. Nature 521, 61–64 (2015)
Chua, L.O.: Cellular neural networks: theory. IEEE Trans. Circuites Syst. 32, 1257–1272 (1988)
Kimura, M.: Neural network using thin-film transistors -working confirmation of asymmetric circuit-. IEICE Technical report, SDM1012-123, 47-52 (2012)
Kimura, M., Miyatani, T., Fujita, Y., Kasakawa, T.: Apoptotic self-organized electronic device using thin-film transistors for artificial neural networks with unsupervised learning functions. Jpn. J. Appl. Phys. 54, 03CB02 (2015)
Nomura, K., Ohta, H., Takagi, A., Kamiya, T., Hirano, M., Hosono, H.: Room-temperature fabrication of transparent flexible thin-film transistors using amorphous oxide semiconductors. Nature 432, 488–492 (2004)
Kimura, M., Imai, S.: Degradation evaluation of a-IGZO TFTs for application to AM-OLEDs. IEEE Electron Device Lett. 31, 963–965 (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Kameda, T., Kimura, M., Nakashima, Y. (2016). Letter Reproduction Simulator for Hardware Design of Cellular Neural Network Using Thin-Film Synapses. In: Hirose, A., Ozawa, S., Doya, K., Ikeda, K., Lee, M., Liu, D. (eds) Neural Information Processing. ICONIP 2016. Lecture Notes in Computer Science(), vol 9948. Springer, Cham. https://doi.org/10.1007/978-3-319-46672-9_39
Download citation
DOI: https://doi.org/10.1007/978-3-319-46672-9_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-46671-2
Online ISBN: 978-3-319-46672-9
eBook Packages: Computer ScienceComputer Science (R0)