Metaheuristic Method for Dimensionality Reduction Tasks

This work demonstrates an alternative training approach, which can be fairly compared with the learning procedures for autoencoders within dimensionality reduction schemes. Therefore, this work's metaheuristic artificial bee colony optimization method trains an encoder-type neural network, whic...

Full description

Saved in:
Bibliographic Details
Main Authors: Anzueto-Rios, A., Gomez-Castaneda, F., Flores-Nava, L.M., Moreno-Cadenas, J.A.
Format: Conference Proceeding
Language:English
Subjects:
Artificial bee colony algorithm
Autoencoder
Dimensionality reduction
Metaheuristics
Neural Network
Neurons
Optimization methods
Training
Transfer functions
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This work demonstrates an alternative training approach, which can be fairly compared with the learning procedures for autoencoders within dimensionality reduction schemes. Therefore, this work's metaheuristic artificial bee colony optimization method trains an encoder-type neural network, which can then compute orthogonal features straight away. Experimental sessions of this method lead us to show competitive results based on public domain datasets.
ISSN:2642-3766
DOI:10.1109/CCE56709.2022.9975991