Self-Improving Generative Artificial Neural Network for Pseudorehearsal Incremental Class Learning

Self-Improving Generative Artificial Neural Network for Pseudorehearsal Incremental Class Learning

Deep learning models are part of the family of artificial neural networks and, as such, they suffer catastrophic interference when learning sequentially. In addition, the greater number of these models have a rigid architecture which prevents the incremental learning of new classes. To overcome thes...

Full description

Bibliographic Details
Main Authors: Diego Mellado, Carolina Saavedra, Steren Chabert, Romina Torres, Rodrigo Salas
Format: Article
Language:English
Published: MDPI AG 2019-10-01
Series:Algorithms
Subjects:
artificial neural networks
deep learning
generative neural networks
incremental learning
novelty detection
catastrophic interference
Online Access:https://www.mdpi.com/1999-4893/12/10/206

Internet

https://www.mdpi.com/1999-4893/12/10/206

Similar Items