"Parallel Training Considered Harmful?": Comparing series-parallel and parallel feedforward network training

Ribeiro, AH; Aguirre, LA

Ribeiro, AH (reprint author), Univ Fed Minas Gerais, Grad Program Elect Engn, Av Antonio Carlos 6627, BR-31270901 Belo Horizonte, MG, Brazil.

NEUROCOMPUTING, 2018; 316 (): 222

Abstract

Neural network models for dynamic systems can be trained either in parallel or in series-parallel configurations. Influenced by early arguments, sever......

Full Text Link