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

no code implementations • 20 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