Full text
|
PDF
- Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (1MB) | Preview |
Adaptive Pointing Theory (APT) Artificial Neural Network
Citation
Al-Rawi, Kamal and Gonzalo Martín, Consuelo (2014). Adaptive Pointing Theory (APT) Artificial Neural Network. "International Journal of Computer and Communication Engineering", v. 3 (n. 3); pp. 212-215. ISSN 2010-3743. https://doi.org/10.7763/IJCCE.2014.V3.322.
Description
| Title: | Adaptive Pointing Theory (APT) Artificial Neural Network |
|---|---|
| Author/s: |
|
| Item Type: | Article |
| Título de Revista/Publicación: | International Journal of Computer and Communication Engineering |
| Date: | May 2014 |
| ISSN: | 2010-3743 |
| Volume: | 3 |
| Subjects: | |
| Freetext Keywords: | Adaptive pointing theory; APT ANN; Adaptive resonance theory; ART ANN; ARTMAP; compact fuzzy ART; artificial neural networks |
| Faculty: | E.T.S. de Ingenieros Informáticos (UPM) |
| Department: | Arquitectura y Tecnología de Sistemas Informáticos |
| Creative Commons Licenses: | Recognition - No derivative works - Non commercial |
Abstract
The choice value and the testing process against the vigilance parameter, characteristic of ART Neural Network, are merged. Only, a single unique test is required to determine if a committed category node can represent the current input or not. Advantages of APT over ART are: 1-Avoid testing every committed category node before deciding to train a committed category node or a new node must be committed, 2-The vigilance parameter is fixed during training, and 3-The choice value parameter is eliminated.
More information
| Item ID: | 35627 |
|---|---|
| DC Identifier: | http://oa.upm.es/35627/ |
| OAI Identifier: | oai:oa.upm.es:35627 |
| DOI: | 10.7763/IJCCE.2014.V3.322 |
| Official URL: | http://www.ijcce.org/ |
| Deposited by: | Memoria Investigacion |
| Deposited on: | 08 Jul 2015 12:10 |
| Last Modified: | 17 Nov 2017 08:54 |
