Abstract
Artificial intelligences are essential concepts in smart societies, and neural networks are typical schemes that imitate human brains. However, the neural networks are conventionally realized using complicated software and high-performance hardware, and the machine size and power consumption are huge. On the other hand, neuromorphic systems are composed solely of optimized hardware, and the machine size and power consumption can be reduced. Therefore, we are investigating neuromorphic systems especially with amorphous metal-oxide semiconductor (AOS) thin-film devices. In this study, we have developed a Hopfield neural network with double-layer AOS thin-film devices as crosspoint-type synapse elements. Here, we propose modified Hebbian learning done locally without extra control circuits, where the conductance deterioration of the crosspoint-type synapse elements can be employed as synaptic plasticity. In order to validate the fundamental operation of the neuromorphic system, first, double-layer AOS thin-film devices as crosspoint-type synapse elements are actually fabricated, and it is found that the electric current continuously decreases along the bias time. Next, a Hopfield neural network is really assembled using a field-programmable gate array (FPGA) chip and the double-layer AOS thin-film devices, and it is confirmed that a necessary function of the letter recognition is obtained after learning process. Once the fundamental operations are confirmed, more advanced functions will be obtained by scaling up the devices and circuits. Therefore, it is expected the neuromorphic systems can be three-dimensional (3D) large-scale integration (LSI) chip, the machine size can be compact, power consumption can be low, and various functions of human brains will be obtained. What has been developed in this study will be the sole solution to realize them.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
McCarthy, J., Minsky, M.L., Rochester, N., Shannon, C.E.: A proposal for the dartmouth summer research project on artificial intelligence. In: Dartmouth Conference (1956)
Russell, S., Norvig, P.: Artificial Intelligence: A Modern Approach. Pearson Education, Prentice Hall (2009)
McCulloch, W.S., Pitts, W.: A logical calculus of the ideas immanent in nervous activity. Bull. Math. Biophys. 5, 115–133 (1943)
Wasserman, P.D.: Neural Computing: Theory and Practice. Coriolis Group, Scottsdale (1989)
Ferrucci, D., et al.: Building watson: an overview of the deep QA project. AI Mag. 31(3), 59–79 (2010)
Merolla, P.A., et al.: A million spiking-neuron integrated circuit with a scalable communication network and interface. Science 345, 668–673 (2014)
Kimura, M., Koga, Y., Nakanishi, H., Matsuda, T., Kameda, T., Nakashima, Y.: In-Ga-Zn-O thin-film devices as synapse elements in a neural network. IEEE J. Electron Devices Soc. 6, 100–105 (2017)
Kameda, T., Kimura, M., Nakashima, Y.: Neuromorphic hardware using simplified elements and thin-film semiconductor devices as synapse elements - simulation of hopfield and cellular neural network. In: Liu, D., Xie, S., Li, Y., Zhao, D., El-Alfy, E.S. (eds.) Neural Information Processing. ICONIP 2017. Lecture Notes in Computer Science, vol. 10639. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-70136-3_81
Hopfield, J.J., Tank, D.W.: Neural computation of decisions in optimization problems. Biol. Cybern. 52, 141–152 (1985)
Hopfield, J.J., Tank, D.W.: Computing with neural circuits: a model. Science 233, 625–633 (1986)
Kimura, M., Morita, R., Sugisaki, S., Matsuda, T., Kameda, T., Nakashima, Y.: Cellular neural network formed by simplified processing elements composed of thin-film transistors. Neurocomputing 248, 112–119 (2017)
Kimura, M., Nakamura, N., Yokoyama, T., Matsuda, T., Kameda, T., Nakashima, Y.: Simplification of processing elements in cellular neural networks. In: Hirose, A., Ozawa, S., Doya, K., Ikeda, K., Lee, M., Liu, D. (eds.) ICONIP 2016. LNCS, vol. 9948, pp. 309–317. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46672-9_35
Chen, Y., et al.: Nanoscale molecular-switch crossbar circuits. Nanotechnol. 14, 462–468 (2003)
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, 1297–1301 (2010)
Merolla, P., Arthur, J., Akopyan, F., Imam, N., Manohar, R., Modha, D.S.: A digital neurosynaptic core using embedded crossbar memory with 45 pJ per Spike in 45 nm. In: 2011 IEEE Custom Integrated Circuits Conference (CICC), pp. 1–4 (2011)
Alibart, F., Zamanidoost, E., Strukov, D.B.: Pattern classification by memristive crossbar circuits using ex situ and in situ training. Nat. Commun. 4, 2072 (2013)
Hu, M., et al.: Dot-product engine for neuromorphic computing: programming 1T1Â M crossbar to accelerate matrix-vector multiplication. In: The 53rd Annual Design Automation Conference (DAC 2016) (2016)
Matsuda, T., Umeda, K., Kato, Y., Nishimoto, D., Furuta, M., Kimura, M.: Rare-Metal-Free High-Performance Ga-Sn-O Thin Film Transistor. Sci. Rep., srep 44326 (2017)
Nomura, K., et al.: Three-dimensionally stacked flexible integrated circuit: amorphous oxide/polymer hybrid complementary inverter using n-type a-In-Ga-Zn-O and p-type poly-(9,9-dioctylfluorene-co-bithiophene) thin-film transistors. Appl. Phys. Lett. 96, 263509 (2010)
Okamoto, R., Fukushima, H., Kimura, M., Matsuda, T.: Characteristic evaluation of Ga-Sn-O films deposited using mist chemical vapor deposition. In: The 2017 International Meeting for Future of Electron Devices, Kansai (IMFEDK 2017), pp. 74–75 (2017)
Prezioso, M., Merrikh-Bayat, F., Hoskins, B.D., Adam, G.C., Likharev, K.K., Strukov, D.B.: Training and operation of an integrated neuromorphic network based on metal-oxide memristors. Nature 521, 61–64 (2015)
Acknowledgments
This work is partially supported by KAKENHI (C) 16K06733, Yazaki Memorial Foundation for Science and Technology, Support Center for Advanced Telecommunications Technology Research, Research Grants in the Natural Sciences from the Mitsubishi Foundation, the Telecommunications Advancement Foundation, RIEC Nation-wide Cooperative Research Projects, collaborative research with ROHM Semiconductor, collaborative research with KOA Corporation, and Innovative Materials and Processing Research Center.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Kimura, M. et al. (2018). Hopfield Neural Network with Double-Layer Amorphous Metal-Oxide Semiconductor Thin-Film Devices as Crosspoint-Type Synapse Elements and Working Confirmation of Letter Recognition. In: Cheng, L., Leung, A., Ozawa, S. (eds) Neural Information Processing. ICONIP 2018. Lecture Notes in Computer Science(), vol 11307. Springer, Cham. https://doi.org/10.1007/978-3-030-04239-4_57
Download citation
DOI: https://doi.org/10.1007/978-3-030-04239-4_57
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-04238-7
Online ISBN: 978-3-030-04239-4
eBook Packages: Computer ScienceComputer Science (R0)