(Invited) Computing with Memristive Devices and Arrays

Abstract

Memristive devices1have become a promising candidate for unconventional computing2due to their attractive properties3. The computing can be implemented on a Resistive Neural Network (ResNN) with memristor synapses and neurons or a Capacitive Neural Network (CapNN) with memcapacitor synapses and neurons. For ResNNs as computing accelerators, we have built a dot-product engine based on a 128 x 64 1T1R crossbar array using traditional non-volatile memristors with 64 stable analog resistance levels4. Accurate image compression and filtering have been demonstrated with such analog computing accelerator4. In addition, we have demonstrated efficient and self-adaptive in-situlearning in a two-layer neural networks using such memristive arrays5, which is expected to significantly improve the speed and energy efficiency of machine learning. For ResNNs beyond accelerator applications, we developed diffusive memristors6with diffusion dynamics that is critical for neuromorphic functions. Based on the diffusive memristors, we have further developed artificial synapses7and neurons8to more faithfully emulate their bio-counterparts. We then integrated these artificial synapses and neurons into a small neural network, with which pattern classification and unsupervised learning have been demonstrated8. For CapNNs, we have developed pseudo-memcapacitive devices based on the diffusive memristors. Capacitive synapses and neurons enabled by these memcapacitive devices have been developed and used to form a fully integrated CapNN9, which has shown spiking signal classification and Hebbian-like learning functions. Moreover, the memristors can be used for cybersecurity10,11, LSTM12and robotics applications13. 1 Xia, Q., Yang, J. J., Memristive crossbar arrays for bio-inspired computing, Nature Materials 18 (2019). 2 Yang, J. J., Strukov, D. B. & Stewart, D. R. Memristive devices for computing. Nature Nanotechnology 8, 13 (2013). 3 Pi, S.et al.Memristor crossbar arrays with 6-nm half-pitch and 2-nm critical dimension. Nature Nanotechnology 14, 35 (2018). 4 Li, C.et al.Analogue signal and image processing with large memristor crossbars. Nature Electronics 1, 52 (2017). 5 Li, C.et al.Efficient and self-adaptive in-situ learning in multilayer memristive neural networks. Nature communications 9, 2385 (2018). 6 Midya, R.et al.Anatomy of Ag/Hafnia-Based Selectors with 1E10 Nonlinearity. Advanced Materials 29, 1604457 (2017). 7 Wang, Z.et al.Memristors with diffusive dynamics as synaptic emulators for neuromorphic computing. Nature Materials 16, 101 (2017). 8 Wang, Z.et al.Fully memristive neural networks for pattern classification with unsupervised learning. Nature Electronics 1, 137 (2018). 9 Wang, Z.et al.Capacitive neural network with neuro-transistors. Nature Communications 9, 3208 (2018). 10 Jiang, H.et al.A Novel True Random Number Generator Based on a Stochastic Diffusive Memristor.Nature communications 8, 882 (2017). 11 Jiang, H.et al.Provable Key Destruction with Large Memristor Crossbars. Nature Electronics 1, 548 (2018). 12 Li, C.et al.Long short-term memory networks in memristor crossbars. Nature Machine Intelligence 1, 49 (2019). 13 Yoon, J. H.et al.An artificial nociceptor based on a diffusive memristor. Nature Communications 9, 417 (2018).