Reservoir computing using dynamic memristors for temporal information processing

Reservoir computing systems utilize dynamic reservoirs having short-term memory to project features from the temporal inputs into a high-dimensional feature space. A readout function layer can then effectively analyze the projected features for tasks, such as classification and time-series analysis. The system can efficiently compute complex and temporal data with low-training cost, since only the readout function needs to be trained. Here we experimentally implement a reservoir computing system using a dynamic memristor array. We show that the internal ionic dynamic processes of memristors allow the memristor-based reservoir to directly process information in the temporal domain, and demonstrate that even a small hardware system with only 88 memristors can already be used for tasks, such as handwritten digit recognition. The system is also used to experimentally solve a second-order nonlinear task, and can successfully predict the expected output without knowing the form of the original dynamic transfer function.Reservoir computing facilitates the projection of temporal input signals onto a high-dimensional feature space via a dynamic system, known as the reservoir. Du et al. realise this concept using metal-oxide-based memristors with short-term memory to perform digit recognition tasks and solve non-linear problems.

[1]  Yann LeCun,et al.  The mnist database of handwritten digits , 2005 .

[2]  Laurent Larger,et al.  High-Speed Photonic Reservoir Computing Using a Time-Delay-Based Architecture: Million Words per Second Classification , 2017 .

[3]  Wei Yang Lu,et al.  Nanoscale memristor device as synapse in neuromorphic systems. , 2010, Nano letters.

[4]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[5]  Bin Wang,et al.  FPGA based spike-time dependent encoder and reservoir design in neuromorphic computing processors , 2016, Microprocess. Microsystems.

[6]  Fabien Alibart,et al.  Pattern classification by memristive crossbar circuits using ex situ and in situ training , 2013, Nature Communications.

[7]  L. Appeltant,et al.  Information processing using a single dynamical node as complex system , 2011, Nature communications.

[8]  Henry Markram,et al.  Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations , 2002, Neural Computation.

[9]  T. Hasegawa,et al.  Short-term plasticity and long-term potentiation mimicked in single inorganic synapses. , 2011, Nature materials.

[10]  Yuchao Yang,et al.  Observation of conducting filament growth in nanoscale resistive memories , 2012, Nature Communications.

[11]  J. Yang,et al.  Memristors with diffusive dynamics as synaptic emulators for neuromorphic computing. , 2017, Nature materials.

[12]  Masakazu Aono,et al.  A theoretical and experimental study of neuromorphic atomic switch networks for reservoir computing , 2013, Nanotechnology.

[13]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[14]  Geert Morthier,et al.  Experimental demonstration of reservoir computing on a silicon photonics chip , 2014, Nature Communications.

[15]  Farnood Merrikh-Bayat,et al.  Training and operation of an integrated neuromorphic network based on metal-oxide memristors , 2014, Nature.

[16]  R. Waser,et al.  Nanoionics-based resistive switching memories. , 2007, Nature materials.

[17]  Kinam Kim,et al.  In situ observation of filamentary conducting channels in an asymmetric Ta2O5−x/TaO2−x bilayer structure , 2013, Nature Communications.

[18]  J Joshua Yang,et al.  Memristive devices for computing. , 2013, Nature nanotechnology.

[19]  Wei Lu,et al.  Short-term Memory to Long-term Memory Transition in a Nanoscale Memristor , 2022 .

[20]  Amir F. Atiya,et al.  New results on recurrent network training: unifying the algorithms and accelerating convergence , 2000, IEEE Trans. Neural Networks Learn. Syst..

[21]  Massimiliano Di Ventra,et al.  Neuromorphic, Digital, and Quantum Computation With Memory Circuit Elements , 2010, Proceedings of the IEEE.

[22]  Wei D. Lu,et al.  Sparse coding with memristor networks. , 2017, Nature nanotechnology.

[23]  Herbert Jaeger,et al.  Reservoir computing approaches to recurrent neural network training , 2009, Comput. Sci. Rev..

[24]  L. Chua.  Memristor-The missing circuit element , 1971 .

[25]  Benjamin Schrauwen,et al.  An experimental unification of reservoir computing methods , 2007, Neural Networks.

[26]  Benjamin Schrauwen,et al.  Memristor Models for Machine Learning , 2014, Neural Computation.

[27]  Dhireesha Kudithipudi,et al.  Memristive Reservoir Computing Architecture for Epileptic Seizure Detection , 2014, BICA.

[28]  Harald Haas,et al.  Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication , 2004, Science.

[29]  Wei Lu,et al.  Biorealistic Implementation of Synaptic Functions with Oxide Memristors through Internal Ionic Dynamics , 2015 .

[30]  Sungho Kim,et al.  Experimental demonstration of a second-order memristor and its ability to biorealistically implement synaptic plasticity. , 2015, Nano letters.

[31]  Cory Merkel,et al.  Design and Analysis of a Neuromemristive Reservoir Computing Architecture for Biosignal Processing , 2016, Front. Neurosci..

[32]  D. Stewart,et al.  The missing memristor found , 2008, Nature.