Training of an Extreme Learning Machine Autoencoder Based on an Iterative Shrinkage-Thresholding Optimization Algorithm

Training of an Extreme Learning Machine Autoencoder Based on an Iterative Shrinkage-Thresholding Optimization Algorithm

Orthogonal transformations, proper decomposition, and the Moore–Penrose inverse are traditional methods of obtaining the output layer weights for an extreme learning machine autoencoder. However, an increase in the number of hidden neurons causes higher convergence times and computational complexity...

Full description

Bibliographic Details
Main Authors: José A. Vásquez-Coronel, Marco Mora, Karina Vilches
Format: Article
Language:English
Published: MDPI AG 2022-09-01
Series:Applied Sciences
Subjects:
autoencoder
feature extraction
extreme learning machine
shrinkage-thresholding algorithms
Online Access:https://www.mdpi.com/2076-3417/12/18/9021

Similar Items

Similar Items