A Fast Neural Network Learning Algorithm with Approximate Singular Value Decomposition

A Fast Neural Network Learning Algorithm with Approximate Singular Value Decomposition

The learning of neural networks is becoming more and more important. Researchers have constructed dozens of learning algorithms, but it is still necessary to develop faster, more flexible, or more accurate learning algorithms. With fast learning we can examine more learning scenarios for a given pro...

Full description

Bibliographic Details
Main Authors: Jankowski Norbert, Linowiecki Rafał
Format: Article
Language:English
Published: Sciendo 2019-09-01
Series:International Journal of Applied Mathematics and Computer Science
Subjects:
moore–penrose pseudo-inverse learning
radial basis function network
extreme learning machines
kernel methods
machine learning
singular value decomposition
deep extreme learning
principal component analysis
Online Access:https://doi.org/10.2478/amcs-2019-0043

Internet

https://doi.org/10.2478/amcs-2019-0043

Similar Items