View(s) :
1 (0 ULiège)
Download(s) :
0 (0 ULiège)
Abstract
This approach presents a possible solution to the stability-plasticity dilemma in incremental neural networks with a local insertion criterion. The main advantages are I) the capability of life-long learning, i.e., learning throughout the entire lifetime of a neural network, ii) stability in a stationary environment and iii) plasticity in a non-stationary environment, but only if the current knowledge does not fit the need of the task. Thus, the network structures its internal representation not like a copy of the environment but in order to fulfill the current task.
Text
References
Bibliographical reference
Fred Henrik Hamker, « Life-long learning in incremental neural networks », CASYS, 3 | 1999, 65-74.
Electronic reference
Fred Henrik Hamker, « Life-long learning in incremental neural networks », CASYS [Online], 3 | 1999, Online since 08 October 2024, connection on 27 December 2024. URL : http://popups.uliege.be/3041-539x/index.php?id=804
Author
Fred Henrik Hamker
Technische Universitiit Ilmenau, Neuroinformatik, D-98684 Ilmenau, Germany