Eigenvalues of Rx — properties of the error surface

Author(s):  
Alexander D. Poularikas ◽  
Zayed M. Ramadan
Keyword(s):  
2002 ◽  
Vol 14 (7) ◽  
pp. 1755-1769 ◽  
Author(s):  
Robert M. French ◽  
Nick Chater

In error-driven distributed feedforward networks, new information typically interferes, sometimes severely, with previously learned information. We show how noise can be used to approximate the error surface of previously learned information. By combining this approximated error surface with the error surface associated with the new information to be learned, the network's retention of previously learned items can be improved and catastrophic interference significantly reduced. Further, we show that the noise-generated error surface is produced using only first-derivative information and without recourse to any explicit error information.


1990 ◽  
Vol 26 (9) ◽  
pp. 587 ◽  
Author(s):  
J.F. Chicharo

2020 ◽  
Vol 2020 (3) ◽  
pp. 3995-3999
Author(s):  
Kamil Zidek ◽  
Jan Pitel ◽  
Alexander Hosovsky ◽  
Natalia Lishchenko ◽  
Martin Miskiv-Pavlik ◽  
...  

Author(s):  
Zhihua Liu ◽  
Zhijing Zhang ◽  
Xin Jing ◽  
Weiming Zhang ◽  
Zifu Wang ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document