Reservoir computing using dynamic memristors for temporal information processing

By Chao Du, Fuxi Cai, Mohammed Affan Zidan, Wen Ma, Seung Hwan Lee, W. Lu. Nature Communications, 2017

901 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Cognitive Neuroscience, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/784a936a088776f44cfc664073ad69a0f036a205

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Cognitive Neuroscience

In Electrical and Electronic Engineering

Citations in the corpus

In-sensor reservoir computing system for latent fingerprint recognition with deep ultraviolet photo-synapses and memristor array (2022, positive): “Recently, emerging devices have been developed for RC system to condense or process spatio-temporal information with higher energy ef ﬁ ciency beyond CMOS technology 19 – 21 .”
Recent Advances in Physical Reservoir Computing: A Review (2018, background): “7(b) (Du et al., 2017), where the reservoir is not a network of memristors but a group of independent memristors.”
In-sensor reservoir computing for language learning via two-dimensional memristors (2021, background): “Thus far, RC systems have been physically implemented on conventional digital platforms and previously unidentified hardware dynamic systems powered by different physical mechanisms (e.g., electronic, photonic, spintronic, mechanical, and biological RC implementations) ( 6 , 9 , 13 – 18 ).”
Experimental photonic quantum memristor (2021, background): “These structures have proven very effective in many relevant tasks, such as speech recognition [18] or image classification [19] and nowadays form the core of the most advanced artificial intelligence algorithms [20].”
Memory devices and applications for in-memory computing (2020, background): “…as well as resistance-based memory devices, is poised to have a significant impact on improving the energy/area efficiency as well as the latency compared to conventional computing systems and given the conducive market environment, this could usher in a new era of non-von Neumann computing.”
Emerging opportunities and challenges for the future of reservoir computing (2024, methodology): “…in experimental settings and an active line of researchistoexplorenewtypesofnonlineardynamicssuchaselectro-optic phase-delay dynamics 28 – 30 , optical scattering 31,32 , dynamic memristors 33 – 36 , enlarged memory capacity in chaotic dynamics 37 , solitons 38 and quantum states 39,40 .”