Reservoir computing using dynamic memristors for temporal information processing

Abstract

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.

Analog–Digital Hybrid Memristive Devices for Image Pattern Recognition with Tunable Learning Accuracy and Speed

“…Its conductance represents the strength of the connection between two neurons, which can be dynamically modulated through external stimuli . Recently, many reports have demonstrated the possibility of neuromorphic system learning by employing memristive ANNs for applications such as pattern recognition, classification, and clustering . Among them, pattern recognition is an important task for developing intelligent computers capable of assisting or replacing humans in dangerous or tedious tasks .…”

Memristor‐Based Biologically Plausible Memory Based on Discrete and Continuous Attractor Networks for Neuromorphic Systems

“…By cascading CANN with other computing units, such as reservoir computing, the total system can have better dynamic information processing capability because CANN can constrain external input into a specific form and be able to temporarily remember external stimulus in the network level. Previous studies have shown the application of memristors in reservoir computing, and suggested that combination of discrete attractor neural network with reservoir computing can have better performance, showcased by the generation of handwritten numbers . Using attractors to constrain the complex dynamics in reservoir will help the computing system converge faster and avoid sustained oscillations.…”

Artificial Perception Built on Memristive System: Visual, Auditory, and Tactile Sensations

“…d) CMOS‐based neuromorphic chips and their key parameters . e) The development of memristive neuromorphic chips shows an exponential scaling‐up trend …”

“…Therefore, using memristors to emulate an artificial synapse, various synaptic functions, including long‐term plasticity, short‐term plasticity, spike‐timing‐dependent plasticity, and spike‐rating‐dependent plasticity, have been established . By assimilating memristors in networks, complex computational functions, such as image classification, image multilayer perceptron, sparse coding, reservoir computing, deep neural networks, and face classification, have been demonstrated. These demonstrations have proved that most of the prevailing machine learning and deep learning algorithms, including feed forward and feedback propagation, can be implemented using a memristive synapse network.…”