ECG Denoising using a Single-Node Dynamic Reservoir Computing Architecture. (Dept. E)

2021 ◽  
Vol 46 (4) ◽  
pp. 47-52
Author(s):  
Aya N. Elbedwehy ◽  
Mohy Eldin Abo-Elsoud ◽  
Ahmed Elnakib
Keyword(s):  
Reservoir Computing ◽  
Single Node ◽  
Computing Architecture ◽  
Ecg Denoising

A Single-Node Classifier Implementation on Chua Oscillator within a Physical Reservoir Computing Framework

2021 ◽  
Vol 31 (11) ◽  
pp. 2150161
Author(s):  
Uladzislau Sychou
Keyword(s):  
Computer Simulation ◽  
Control Parameter ◽  
Chaotic Oscillator ◽  
Reservoir Computing ◽  
Single Node ◽  
Short Pulses ◽  
Chaotic Mode ◽  
Computing Framework ◽  
Chua Oscillator

The study lies in the field of physical reservoir computing and aims to develop a classifier using Fisher Iris dataset for benchmark tasks. Single Chua chaotic oscillator acts as a physical reservoir. The study was performed using computer simulation. The features of Iris flowers are represented as the consequence of short pulses at a constant level of a control parameter, which is fed to the oscillator, changing its dynamics. During the classification of flowers, the oscillator works without being reset, so each pulse on the input changes the phase trajectory and makes it unique for each Iris flower. Finally, the estimation of the symmetry of an attractor makes it possible to connect each species of Iris with the properties of the attractor. The resulting architecture of the classifier includes a single-node externally-driven Chua oscillator with time-delayed input. The classifier shows two mistakes in classifying the dataset with 75 samples working in chaotic mode.

scholarly journals Design and Analysis of a Neuromemristive Reservoir Computing Architecture for Biosignal Processing

2016 ◽  
Vol 9 ◽  
Author(s):  
Dhireesha Kudithipudi ◽  
Qutaiba Saleh ◽  
Cory Merkel ◽  
James Thesing ◽  
Bryant Wysocki
Keyword(s):  
Reservoir Computing ◽  
Computing Architecture ◽  
Biosignal Processing

scholarly journals Memristive Reservoir Computing Architecture for Epileptic Seizure Detection

2014 ◽  
Vol 41 ◽  
pp. 249-254 ◽  
Author(s):  
Cory Merkel ◽  
Qutaiba Saleh ◽  
Colin Donahue ◽  
Dhireesha Kudithipudi
Keyword(s):  
Epileptic Seizure ◽  
Seizure Detection ◽  
Reservoir Computing ◽  
Epileptic Seizure Detection ◽  
Computing Architecture

scholarly journals Persistent Memory in Single Node Delay-Coupled Reservoir Computing

PLoS ONE ◽  
2016 ◽  
Vol 11 (10) ◽  
pp. e0165170 ◽  
Author(s):  
André David Kovac ◽  
Maximilian Koall ◽  
Gordon Pipa ◽  
Hazem Toutounji
Keyword(s):  
Reservoir Computing ◽  
Single Node ◽  
Persistent Memory

scholarly journals Homeostatic Plasticity for Single Node Delay-Coupled Reservoir Computing

2015 ◽  
Vol 27 (6) ◽  
pp. 1159-1185 ◽  
Author(s):  
Hazem Toutounji ◽  
Johannes Schumacher ◽  
Gordon Pipa
Keyword(s):  
Homeostatic Plasticity ◽  
Reservoir Computing ◽  
Computational Power ◽  
Biologically Inspired ◽  
Single Node ◽  
Plasticity Mechanism ◽  
Learning Mechanism ◽  
Infinite Dimensional ◽  
Dimensional Dynamical System ◽  
Infinite Dimensional Dynamical System

Supplementing a differential equation with delays results in an infinite-dimensional dynamical system. This property provides the basis for a reservoir computing architecture, where the recurrent neural network is replaced by a single nonlinear node, delay-coupled to itself. Instead of the spatial topology of a network, subunits in the delay-coupled reservoir are multiplexed in time along one delay span of the system. The computational power of the reservoir is contingent on this temporal multiplexing. Here, we learn optimal temporal multiplexing by means of a biologically inspired homeostatic plasticity mechanism. Plasticity acts locally and changes the distances between the subunits along the delay, depending on how responsive these subunits are to the input. After analytically deriving the learning mechanism, we illustrate its role in improving the reservoir’s computational power. To this end, we investigate, first, the increase of the reservoir’s memory capacity. Second, we predict a NARMA-10 time series, showing that plasticity reduces the normalized root-mean-square error by more than 20%. Third, we discuss plasticity’s influence on the reservoir’s input-information capacity, the coupling strength between subunits, and the distribution of the readout coefficients.

A Distributed-Ledger, Edge-Computing Architecture for Automation and Computer Integration in Semiconductor Manufacturing

2020 ◽  
pp. 13-29
Author(s):  
Da-Yin Liao
Keyword(s):  
Semiconductor Manufacturing ◽  
Manufacturing Systems ◽  
Edge Computing ◽  
Legacy Systems ◽  
Software Framework ◽  
Computer Integration ◽  
Computing Architecture ◽  
Disruptive Technologies ◽  
Distributed Ledger ◽  
Operational Structure

Contemporary 300mm semiconductor manufacturing systems have highly automated and digitalized cyber-physical integration. They suffer from the profound problems of integrating large, centralized legacy systems with small islands of automation. With the recent advances in disruptive technologies, semiconductor manufacturing has faced dramatic pressures to reengineer its automation and computer integrated systems. This paper proposes a Distributed-Ledger, Edge-Computing Architecture (DLECA) for automation and computer integration in semiconductor manufacturing. Based on distributed ledger and edge computing technologies, DLECA establishes a decentralized software framework where manufacturing data are stored in distributed ledgers and processed locally by executing smart contracts at the edge nodes. We adopt an important topic of automation and computer integration for semiconductor research &development (R&D) operations as the study vehicle to illustrate the operational structure and functionality, applications, and feasibility of the proposed DLECA software framework.

Sign in / Sign up

Export Citation Format

Share Document