Transfer Learning for Algorithm Recommendation

no code implementations • 15 Oct 2019 • Gean Trindade Pereira, Moisés dos Santos, Edesio Alcobaça, Rafael Mantovani, André Carvalho

Thus, we train a neural network on meta-datasets related to algorithm recommendation, and then using transfer learning, we reuse the knowledge learned by the neural network in other similar datasets from the same domain, to verify how transferable is the acquired meta-knowledge.

BIG-bench Machine Learning Image Classification +5