Model-size reduction for the analysis of symmetric structures with asymmetric boundary conditions

1987 ◽  
Vol 24 (5) ◽  
pp. 913-926 ◽  
Author(s):  
Ahmed K. Noor ◽  
Sandra L. Whitworth
Author(s):  
Caojin Zhang ◽  
Yicun Liu ◽  
Yuanpu Xie ◽  
Sofia Ira Ktena ◽  
Alykhan Tejani ◽  
...  

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Yusuke Sakemi ◽  
Kai Morino ◽  
Timothée Leleu ◽  
Kazuyuki Aihara

AbstractReservoir computing (RC) is a machine learning algorithm that can learn complex time series from data very rapidly based on the use of high-dimensional dynamical systems, such as random networks of neurons, called “reservoirs.” To implement RC in edge computing, it is highly important to reduce the amount of computational resources that RC requires. In this study, we propose methods that reduce the size of the reservoir by inputting the past or drifting states of the reservoir to the output layer at the current time step. To elucidate the mechanism of model-size reduction, the proposed methods are analyzed based on information processing capacity proposed by Dambre et al. (Sci Rep 2:514, 2012). In addition, we evaluate the effectiveness of the proposed methods on time-series prediction tasks: the generalized Hénon-map and NARMA. On these tasks, we found that the proposed methods were able to reduce the size of the reservoir up to one tenth without a substantial increase in regression error.


2000 ◽  
Vol 33 (1) ◽  
pp. 1-14 ◽  
Author(s):  
Elena Palomo Del Barrio ◽  
Gilles Lefebvre ◽  
Philippe Behar ◽  
Noël Bailly

Sign in / Sign up

Export Citation Format

Share Document