Investigation of multi-layer neural network performance evolved by genetic algorithms

This paper presents a study on the investigation of multi-layer neural networks (MLNNs) performance evolved with genetic algorithm (GA) for multi-logic training patterns applied to various network functions. Specifically, we have concentrated on the Sigmoid, Step and ReLU functions to evaluate and s...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Artificial life and robotics 2019-06, Vol.24 (2), p.183-188
Hauptverfasser:	Betere, Isaac Job, Kinjo, Hiroshi, Nakazono, Kunihiko, Oshiro, Naoki
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial Intelligence Computation by Abstract Devices Computer Science Computer simulation Control Evolutionary algorithms Genetic algorithms Mechatronics Multilayers Neural networks Original Article Robotics Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!