no code implementations • 17 Feb 2021 • Alejandro Barredo Arrieta, Sergio Gil-Lopez, Ibai Laña, Miren Nekane Bilbao, Javier Del Ser
Specifically, the study proposes three different techniques capable of eliciting understandable information about the knowledge grasped by these recurrent models, namely, potential memory, temporal patterns and pixel absence effect.
no code implementations • 17 Apr 2020 • Javier Del Ser, Ibai Lana, Eric L. Manibardo, Izaskun Oregi, Eneko Osaba, Jesus L. Lobo, Miren Nekane Bilbao, Eleni I. Vlahogianni
Results from this comparison benchmark and the analysis of the statistical significance of the reported performance gaps are decisive: Deep Echo State Networks achieve more accurate traffic forecasts than the rest of considered modeling counterparts.