An introduction to artificial neural networks
| dc.creator | Bailer-Jones, C. A. L. | |
| dc.creator | Gupta, R. | |
| dc.creator | Singh, H. P. | |
| dc.date | 2001-02-13 | |
| dc.date.accessioned | 2026-07-07T01:57:42Z | |
| dc.date.available | 2026-07-07T01:57:42Z | |
| dc.description | Artificial neural networks are algorithms which have been developed to tackle a range of computational problems. These range from modelling brain function to making predictions of time-dependent phenomena to solving hard (NP-complete) problems. In this introduction we describe a single, yet very important, type of network known as a feedforward network. This network is a mathematical model which can be trained to learn an arbitrarily complex relationship between a data and a parameter domain, so can be used to solve interpolation and classification problems. We discuss the structure, training and interpretation of these networks, and their implementation, taking the classification of stellar spectra as an example. | |
| dc.description | To appear in "Automated Data Analysis in Astronomy", R. Gupta, H.P. Singh, C.A.L. Bailer-Jones (eds.), Narosa Publishing House, New Delhi, India, 2001. 18 pages, 8 figures. Also available from http://www.mpia-hd.mpg.de/homes/calj/annintro.html | |
| dc.identifier | https://arxiv.org/abs/astro-ph/0102224 | |
| dc.identifier | http://arxiv.org/abs/astro-ph/0102224 | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/2488 | |
| dc.subject | Astrophysics | |
| dc.title | An introduction to artificial neural networks | |
| dc.type | text |