Efficient hyperparameter optimization in convolutional neural networks by learning curves prediction

Conference Object

Abstract: In this work, we present an automatic framework for hyperparameter selection in Convolutional Neural

Palabras claves:

deep learning, forecasting, Hyperparameter optimization, Learning curves, Singular spectrum analysis, SVR

Autores:

A. E. Castro-Ospina, Cardona-Escobar A., Giraldo-Forero A., Jaramillo-Garzon J.A.

Fuentes:

scopus