Search Results for author: Daniel Molina

Found 8 papers, 2 papers with code

Multiobjective Evolutionary Pruning of Deep Neural Networks with Transfer Learning for improving their Performance and Robustness

no code implementations20 Feb 2023 Javier Poyatos, Daniel Molina, Aitor Martínez, Javier Del Ser, Francisco Herrera

MO-EvoPruneDeepTL uses Transfer Learning to adapt the last layers of Deep Neural Networks, by replacing them with sparse layers evolved by a genetic algorithm, which guides the evolution based in the performance, complexity and robustness of the network, being the robustness a great quality indicator for the evolved models.

Neural Architecture Search Transfer Learning

EvoPruneDeepTL: An Evolutionary Pruning Model for Transfer Learning based Deep Neural Networks

1 code implementation8 Feb 2022 Javier Poyatos, Daniel Molina, Aritz. D. Martinez, Javier Del Ser, Francisco Herrera

Depending on its solution encoding strategy, our proposed model can either perform optimized pruning or feature selection over the densely connected part of the neural network.

Computational Efficiency feature selection +1

Lights and Shadows in Evolutionary Deep Learning: Taxonomy, Critical Methodological Analysis, Cases of Study, Learned Lessons, Recommendations and Challenges

no code implementations9 Aug 2020 Aritz D. Martinez, Javier Del Ser, Esther Villar-Rodriguez, Eneko Osaba, Javier Poyatos, Siham Tabik, Daniel Molina, Francisco Herrera

In summary, three axes - optimization and taxonomy, critical analysis, and challenges - which outline a complete vision of a merger of two technologies drawing up an exciting future for this area of fusion research.

Cannot find the paper you are looking for? You can Submit a new open access paper.