Application of Levenberg-Marquardt method to the training of spiking neural networks

2006 ◽  
Author(s):  
S.M. Silva ◽  
A.E. Ruano
Keyword(s):  
Neural Networks ◽  
Spiking Neural Networks ◽  
Marquardt Method ◽  
Levenberg Marquardt

scholarly journals Jaringan Saraf Tiruan dalam Memprediksi Produksi Kelapa Sawit di PT. KRE Menggunakan Algoritma Levenberg Marquardt

2019 ◽  
Vol 1 ◽  
pp. 249
Author(s):  
Yuli Andriani ◽  
Anjar Wanto ◽  
Handrizal Handrizal
Keyword(s):  
Neural Networks ◽  
Secondary Data ◽  
Research Data ◽  
Training Data ◽  
Accuracy Rate ◽  
Marquardt Method ◽  
Rate Of Increase ◽  
Testing Data ◽  
Levenberg Marquardt ◽  
Architectural Models

Predictions are used to determine how much the rate of increase or decrease in oil palm production at PT. Kerasaan Indonesia (KRE) in the future. This study uses Artificial Neural Networks (ANN) using the Levenberg Marquardt method. The research data is secondary data sourced from PT. Kerasaan Indonesia from 2002 to 2017. Data is divided into 2 parts, namely training data and testing data. There are 5 architectural models used in this study, 7-10-1, 7-20-1, 7-30-1, 7-40-1 and 7-50-1. Of the 5 architectural models used, the best architecture is 7-50-1 by producing an accuracy rate of 83%, MSE 1.1471332321 and a maximum iteration of 1000. So this model is good for predicting coconut production palm oil at PT. Indonesian feeling because of its accuracy between 80% and 90%.

A Developmental Method for Evolving Large-Scale Spiking Neural Networks

2012 ◽  
Vol 35 (12) ◽  
pp. 2633 ◽  
Author(s):  
Xiang-Hong LIN ◽  
Tian-Wen ZHANG ◽  
Gui-Cang ZHANG
Keyword(s):  
Neural Networks ◽  
Large Scale ◽  
Spiking Neural Networks

scholarly journals Spiking Neural Networks and online learning: An overview and perspectives

2020 ◽  
Vol 121 ◽  
pp. 88-100 ◽  
Author(s):  
Jesus L. Lobo ◽  
Javier Del Ser ◽  
Albert Bifet ◽  
Nikola Kasabov
Keyword(s):  
Neural Networks ◽  
Online Learning ◽  
Spiking Neural Networks
Sign in / Sign up

Export Citation Format

Share Document