2026-06-05T04:07:28Zhttps://riuma.uma.es/rest/oai/request

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

A novel continual learning approach for competitive neural networks Fernández-Rodríguez, Jose David Maza Quiroga, Rosa María Palomo-Ferrer, Esteban José Ortiz-de-Lazcano-Lobato, Juan Miguel López-Rubio, Ezequiel Redes neuronales (Informática) Aprendizaje automático (Inteligencia artificial) Aprendizaje 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. 2022-06-14T10:11:20Z 2022-06-14T10:11:20Z 2022-06-14T10:11:20Z 2022 conference output https://hdl.handle.net/10630/24361 eng 9th International Work-Conference on the Interplay Between Natural and Artificial Computation Puerto de la Cruz (Tenerife), España 31 mayo /2022 open access