Andras - IJCNN 2018.pdf
(378 Kb)
PDF
Random Projection Neural Network Approximation
Abstract
Neural networks are often used to approximate functions defined over high-dimensional data spaces (e.g. text data, genomic data, multi-sensor data). Such approximation tasks are usually difficult due to the curse of dimensionality and improved methods are needed to deal with them effectively and efficiently. Since the data generally resides on a lower dimensional manifold various methods have been proposed to project the data first into a lower dimension and then build the neural network approximation over this lower dimensional projection data space. Here we follow this approach and combine it with the idea of weak learning through the use of random projections of the data. We show that random projection of the data works well and the approximation errors are smaller than in the case of approximation of the functions in the original data space. We explore the random projections with the aim to optimize this approach.
Acceptance Date | Mar 15, 2018 |
---|---|
Publication Date | Jul 1, 2018 |
Publicly Available Date | Mar 29, 2024 |
Journal | 2017 International Joint Conference on Neural Networks (IJCNN 2017) |
Series Title | International Joint Conference on Neural Networks (IJCNN) 2018 |
DOI | https://doi.org/10.1109/ijcnn.2018.8489215 |
Keywords | function approximation, high-dimensional, neural network, random projection, weak learning |
Publisher URL | https://doi.org/10.1109/ijcnn.2018.8489215 |
Files
Downloadable Citations
About Keele Repository
Administrator e-mail: research.openaccess@keele.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2024
Advanced Search