2026-06-03T03:10:30Zhttps://riuma.uma.es/rest/oai/request

oai:riuma.uma.es:10630/243612026-02-03T12:21:24Zcom_10630_2254col_10630_37959

00925njm 22002777a 4500 dc Fernández-Rodríguez, Jose David author Maza Quiroga, Rosa María author Palomo-Ferrer, Esteban José author Ortiz-de-Lazcano-Lobato, Juan Miguel author López-Rubio, Ezequiel author 2022 Continual learning tries to address the stability-plasticity dilemma to avoid catastrophic forgetting when dealing with non-stationary distributions. Prior works focused on supervised or reinforcement learning, but few works have considered continual learning for unsupervised learning methods. In this paper, a novel approach to provide continual learning for competitive neural networks is proposed. To this end, we have proposed a different learning rate function that can cope with non-stationary distributions by adapting the model to learn continuously. Experimental results performed with different synthetic images that change over time confirm the performance of our proposal. https://hdl.handle.net/10630/24361 Redes neuronales (Informática) Aprendizaje automático (Inteligencia artificial) Aprendizaje A novel continual learning approach for competitive neural networks