dc.creator | Vásquez-Coronel, José A | |
dc.creator | Mora, Marco | |
dc.creator | Vilches-Ponce, Karina | |
dc.creator | Silva Pavez, Fabián | |
dc.creator | Torres-Gonzalez, Italo | |
dc.creator | Barria-Valdevenito, Pedro | |
dc.date | 2023-03-08T13:28:10Z | |
dc.date | 2023-03-08T13:28:10Z | |
dc.date | 2022 | |
dc.date.accessioned | 2024-05-02T20:30:38Z | |
dc.date.available | 2024-05-02T20:30:38Z | |
dc.identifier | http://repositorio.ucm.cl/handle/ucm/4494 | |
dc.identifier.uri | https://repositorioslatinoamericanos.uchile.cl/handle/2250/9274738 | |
dc.description | Autoencoders are neural networks that are characterized by having the same inputs and outputs. This kind of Neural Networks aim to estimate a nonlinear transformation whose parameters allow to represent the input patterns to the network. The Extreme Learning Machine (ELM-AE) Autoencoders have random weights and biases in the hidden layer, and compute the output parameters by solving an overdetermined linear system using the Moore-Penrose Pseudoinverse. ELM-AE training is based on the Fast Iterative Shrinkage-Thresholding (FISTA). In this paper, we propose to improve the convergence speed obtained by FISTA considering the use of two algorithms of the Shrinkage-Thresholding class, namely Greedy FISTA and Linearly-Convergent FISTA. 6 frequently used public machine learning datasets were considered: MNIST, NORB, CIFAR10, UMist, Caltech256, Stanford Cars. Experiments were carried out varying the number of neurons in the hidden layer of the Autoencoders, considering the 3 algorithms, for all the databases. The experimental results showed that Greedy FISTA and Linearly-Convergent FISTA presented higher convergence speed, increasing the speed of ELM-Autoencoder training, maintaining a comparable generalization error between the three Shrinkage-Thresholding algorithms. | |
dc.language | en | |
dc.rights | Atribución-NoComercial-SinDerivadas 3.0 Chile | |
dc.rights | http://creativecommons.org/licenses/by-nc-nd/3.0/cl/ | |
dc.source | International Conference on Automation/XXV Congress of the Chilean Association of Automatic Control (ICA-ACCA), Curicó, Chile, 1-7 | |
dc.subject | Training | |
dc.subject | Linear systems | |
dc.subject | Machine learning algorithms | |
dc.subject | Extreme learning machines | |
dc.subject | Databases | |
dc.subject | Neurons | |
dc.subject | Machine learning | |
dc.title | A new fast training algorithm for autoencoder neural networks based on extreme learning machine | |
dc.type | Article | |