Multi-state MRAM cells for hardware neuromorphic computing

  • Fu, J., Zheng, H. & Mei, T. Look closer to see better: recurrent attention convolutional neural network for fine-grained image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition4438–4446 (2017).

  • Venayagamoorthy, GK, Moonasar, V. & Sandrasegaran, K. Speech recognition using neural networks. In Proceedings of the 1998 South African Symposium on Communications and Signal Processing-COMSIG’98 (Cat. No. 98EX214)29–32 (IEEE, 1998).

  • Zhang, Y., Li, S. & Guo, H. A type of distributed neural network based on biased consensus for path planning. Nonlinear dynamics. 891803–1815 (2017).

    MathSciNet ArticleGoogle Scholar

  • Muralitharan, K., Sakthivel, R. & Vishnuvarthan, R. Neural network-based optimization approach for power demand forecasting in smart grids. Neuroinformatics 273199-208 (2018).

    Google Scholar article

  • Abhishek, K., Singh, M., Ghosh, S. & Anand, A. Weather forecasting model using an artificial neural network. proc. Technology. 4311–318 (2012).

    Google Scholar article

  • Nurvitadhi, E. et al. Acceleration of binarized neural networks: comparison between FPGA, CPU, GPU and ASIC. In 2016 International Conference on Field Programmable Technology (FPT)77–84 (IEEE, 2016).

  • Yao, P. et al. Fully hardware-implemented memristor convolutional neural network. Nature 577641–646 (2020).

    ADS CAS Article Google Scholar

  • Yao, P. et al. Face classification using electronic synapses. Nat. Commmon. 81–8 (2017).

    Article on Google Scholar Ads

  • Yu, S. Neuro-inspired computing with emergent non-volatile memories. proc. IEEE 106260-285 (2018).

    CAS Google Scholar Article

  • Ambrogio, S. et al. Accelerated neural network training with equivalent precision using analog memory. Nature 55860–67 (2018).

    ADS CAS Article Google Scholar

  • Strukov, DB, Snider, GS, Stewart, DR & Williams, RS Missing memristor found. Nature 45380–83 (2008).

    ADS CAS Article Google Scholar

  • Burr, GW et al. Neuromorphic computation using non-volatile memory. Adv. Phys. X 2, 89–124. https://doi.org/10.1080/23746149.2016.1259585 (2017).

  • Wu, Q. et al. Improving durability and switching speed by incorporating nanocrystals into HfOx-based resistive RAM devices. Appl. Phys. Lett. 113023105 (2018).

    Article on Google Scholar Ads

  • Grollier, J., Querlioz, D. & Stiles, MD Spintronic Nanodevices for Bioinspired Computing. proc. IEEE 104, 2024-2039. https://doi.org/10.1109/JPROC.2016.2597152 (2016).

    Google Scholar article

  • Borders, WA et al. Integer factorization using stochastic magnetic tunnel junctions. Nature 573, 390–393. https://doi.org/10.1038/s41586-019-1557-9 (2019).

    ADS CAS PubMed Article Google Scholar

  • Romera, M. et al. Vowel recognition with four spin-coupled nano-oscillators. Nature 563, 230–234. https://doi.org/10.1038/s41586-018-0632-y (2018).

    ADS CAS PubMed Article Google Scholar

  • Moons, B., Goetschalckx, K., Van Berckelaer, N. & Verhelst, M. Minimum energy quantized neural networks. In 2017 51st Asilomar Conference on Signals, Systems and Computers1921-1925 (IEEE, 2017).

  • Hubara, I., Courbariaux, M., Soudry, D., El-Yaniv, R. & Bengio, Y. Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations. J.Mach. To learn. Res. 186869–6898 (2017).

    MathSciNet MATHGoogle Scholar

  • Toledo, TG, Perach, B., Soudry, D. & Kvatinsky, S. MTJ-Based Hardware Synapse Design for Quantized Deep Neural Networks. arXiv preprintarXiv:1912.12636 (2019).

  • Rzeszut, P., Skowroński, W., Ziętek, S., Wrona, J., and Stobiecki, T. Multi-bit MRAM storage cells using series-connected perpendicular magnetic tunnel junctions. J.Appl. Phys. 125223907 (2019).

    Article on Google Scholar Ads

  • Raymenants, E. et al. Chain of magnetic tunnel junctions as a spintronic memristor. J.Appl. Phys. 124152116 (2018).

    Article on Google Scholar Ads

  • Zhang, D. et al. All spin artificial neural networks based on compound spintronic synapse and neuron. IEEE Trans. Biomedical. System circuits ten828–836 (2016).

    Google Scholar article

  • Torrejon, J. et al. Neuromorphic computing with nanoscale spintronic oscillators. Nature 547428 (2017).

    CAS Google Scholar Article

  • Lequeux, S. et al. A magnetic synapse: spin-coupled multilevel memristor with perpendicular anisotropy. Science. representing 631510 (2016).

    ADS CAS Article Google Scholar

  • Sung, C., Hwang, H. & Yoo, IK Perspective: A Review of Memristive Material for Neuromorphic Computation. J.Appl. Phys. 124151903 (2018).

    Article on Google Scholar Ads

  • Sulymenko, O. et al. Ultra-fast logic devices using artificial “neurons” based on antiferromagnetic pulse generators. J.Appl. Phys. 124152115 (2018).

    Article on Google Scholar Ads

  • Fukami, S. & Ohno, H. Perspective: spintronic synapse for artificial neural network. J.Appl. Phys. 124151904 (2018).

    Article on Google Scholar Ads

  • Deng, L. The mnist Database of Handwritten Digital Images for Machine Learning Research [best of the web]. IEEE signal process. Mag. 29141–142 (2012).

    Article on Google Scholar Ads

  • Zhang, D., Hou, Y., Zeng, L. & Zhao, W. Hardware-accelerated implementation of sparse coding algorithm with spintronic devices. IEEE Trans. Nanotechnology. 18518–531 (2019).

    ADS CAS Article Google Scholar

  • Amirany, A., Moaiyeri, MH & Jafari, K. Non-volatile associative memory design based on spintronic synapses and cntfet neurons. IEEE Trans. Emergency High. Calculation. 1–1. https://doi.org/10.1109/TETC.2020.3026179 (2020).

  • Mihajlovic, G. et al. Origin of resistance-area-product dependence of spin-transfer-torque switching in perpendicular magnetic random-access memory cells. Phys. Rev. Appl. 13024004 (2020).

    Article on Google Scholar Ads

  • Watanabe, K., Jinnai, B., Fukami, S., Sato, H. & Ohno, H. Revisited shape anisotropy in single-digit nanoscale magnetic tunnel junctions. Nat. Commmon. 91–6 (2018).

    Google Scholar article

  • Khodabandehloo, G., Mirhassani, M. & Ahmadi, M. Analog implementation of a new resistive type sigmoid neuron. IEEE Trans. Integrates on a very large scale. VLSI system 20, 750–754. https://doi.org/10.1109/TVLSI.2011.2109404 (2012).

    Google Scholar article

  • Alzate, J. et al. 2MB array level demonstration of the stt-mram process and performance to l4 cache applications. In IEEE International Electronic Devices Meeting (IEDM) 20192–4 (IEEE, 2019).

  • Sherry J. Basler