Reservoir computing using dynamic memristors for temporal information processing

Резервуарные вычисления с использованием динамических мемристоров для обработки временной информации
Wei Dong Lu, Mohammed Affan Zidan, Chao Du, Wen Ma, Seung Hwan Lee, Fuxi Cai
2017-12-13

dynamic memristorshandwritten digit recognitionreservoir computingshort-term memorytemporal 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.
1
A reservoir computing system was experimentally implemented using a dynamic memristor array.
2
A small hardware system with only 88 memristors can perform tasks such as handwritten digit recognition.
3
Internal ionic dynamics of memristors enable direct processing of temporal-domain information in the reservoir.
4
Reservoir computing with memristors retains low training cost because only the readout layer requires training.
5
The memristor-based reservoir experimentally solved a second-order nonlinear task and predicted outputs without knowing the original transfer function form.

Reservoir computing system implemented using a dynamic memristor array

Temporal information processing capabilities of the memristor-based reservoir, including short-term memory from internal ionic dynamics for tasks like handwritten digit recognition and second-order nonlinear temporal prediction

Publication Details
Publication Date
2017-12-13
Journal
Publisher
ISSN
Cited by
1014
Access Type
Author Information
Authors
Wei Dong Lu
Mohammed Affan Zidan
Chao Du
Wen Ma
Seung Hwan Lee
Fuxi Cai
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%