Designing neural networks for object recognition requires considerable architecture engineering. As a remedy, neuro-evolutionary network architecture search, which automatically searches for optimal network architectures using evolutionary algorithms, has recently become very popular. Although very effective, evolutionary algorithms rely heavily on having a large population of individuals (i.e., network architectures) and are therefore memory expensive. In this work, we propose a Regularized Evolutionary Algorithm with low memory footprint to evolve a dynamic image classifier. In details, we introduce novel custom operators that regularize the evolutionary process of a micro-population of 10 individuals. We conduct experiments on three different digits datasets (MNIST, USPS, SVHN) and show that our evolutionary method obtains competitive results with the current state-of-the-art.
Titolo: | Regularized Evolutionary Algorithm for Dynamic Neural Topology Search |
Autori: | |
Data di pubblicazione: | 2019 |
Serie: | |
Handle: | http://hdl.handle.net/11582/320631 |
ISBN: | 978-3-030-30641-0 978-3-030-30642-7 |
Appare nelle tipologie: | 4.1 Contributo in Atti di convegno |
File in questo prodotto:
File | Descrizione | Tipologia | Licenza | |
---|---|---|---|---|
SalRoySeb_ICIAP_2019.pdf | Articolo principale | N/A | NON PUBBLICO - Accesso privato/ristretto | Utenti riconosciuti Richiedi una copia |