Dynamic Sampling Approach to Training Neural Networks for Multiclass Imbalance Classification

2013 ◽  
Vol 24 (4) ◽  
pp. 647-660 ◽  
Author(s):  
Minlong Lin ◽  
Ke Tang ◽  
Xin Yao
2018 ◽  
Vol 2018 (15) ◽  
pp. 131-1-1316 ◽  
Author(s):  
Yan Zhang ◽  
G. M. Dilshan Godaliyadda ◽  
Nicola Ferrier ◽  
Emine B. Gulsoy ◽  
Charles A. Bouman ◽  
...  

2017 ◽  
Vol 2017 ◽  
pp. 1-10 ◽  
Author(s):  
Jin-E Zhang

In this paper, the globalO(t-α)synchronization problem is investigated for a class of fractional-order neural networks with time delays. Taking into account both better control performance and energy saving, we make the first attempt to introduce centralized data-sampling approach to characterize theO(t-α)synchronization design strategy. A sufficient criterion is given under which the drive-response-based coupled neural networks can achieve globalO(t-α)synchronization. It is worth noting that, by using centralized data-sampling principle, fractional-order Lyapunov-like technique, and fractional-order Leibniz rule, the designed controller performs very well. Two numerical examples are presented to illustrate the efficiency of the proposed centralized data-sampling scheme.


2018 ◽  
Vol 17 ◽  
pp. 1031-1038
Author(s):  
Gian Antonio Susto ◽  
Marco Maggipinto ◽  
Federico Zocco ◽  
Sean McLoone

Sign in / Sign up

Export Citation Format

Share Document