Por favor, use este identificador para citar o enlazar a este item:
http://hdl.handle.net/10261/30288
COMPARTIR / EXPORTAR:
SHARE BASE | |
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE | |
Título: | Minimally disturbing learning |
Autor: | Ruiz de Angulo, Vicente CSIC ORCID ; Torras, Carme CSIC ORCID | Palabras clave: | Learning Catastrophic forgetting On-line learning Backpropagation Distributed representations Automation: Robots Robots Robotics |
Fecha de publicación: | 1991 | Editor: | Springer Nature | Citación: | 1st International Conference on Artificial Neural Networks: 162-172 (1991) | Resumen: | We have undertaken the study of methods for avoiding catastrophic forgetting in feedforward neural networks, without sacrifying the benefits of distributed representations. We formalize the problem as the minimization of the error over the previously learned input-output (i–o) patterns, subject to the constraint of perfect encoding of the new pattern. Then we transform this constrained optimization problem into an unconstrained one. This new formulation naturally leads to an algorithm for solving the problem, wihch we call Minimally Disturbing Learning (MDL). Some experimental comparisons of the performance of MDL with back-propagation are provided which, besides showing the advantages of using MDL, reveal the dependence of forgetting on the learning rate in back-propagation. | Descripción: | International Conference on Artificial Neural Networks (IWANN), 1991, Granada (España) | URI: | http://hdl.handle.net/10261/30288 | DOI: | 10.1007/BFb0035891 | ISBN: | 3540545379 |
Aparece en las colecciones: | (IRII) Comunicaciones congresos |
Ficheros en este ítem:
Fichero | Descripción | Tamaño | Formato | |
---|---|---|---|---|
doc1.pdf | 461,57 kB | Adobe PDF | Visualizar/Abrir |
CORE Recommender
Page view(s)
361
checked on 24-abr-2024
Download(s)
321
checked on 24-abr-2024
Google ScholarTM
Check
Altmetric
Altmetric
NOTA: Los ítems de Digital.CSIC están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.