| |
 |
| Paper: |
Adaptive Resonance Theory Neural Networks for Astronomical Region of Interest Detection and Noise Characterization |
| Volume: |
376, Astronomical Data Analysis Software and Systems XVI |
| Page: |
409 |
| Authors: |
Young, R.J.; Ritthaler, M.; Healy, M.; Caudell, T.P.; Zimmer, P.; McGraw, J. |
| Abstract: |
While learning algorithms have been used for astronomical data analysis, the vast majority of those algorithms have used supervised learning. We examine the use of two types of Adaptive Resonance Theory (ART) (Carpenter & Grossberg 1987) neural networks which use unsupervised learning for this task. Using synthetic astronomical data from SkyMaker which was designed to mimic the dynamic range of the CTI-II telescope, we compared the ability of the ART-1 neural network and the ART-1 neural network with a category theoretic modification to detect regions of interest and to characterize noise. We use the program SExtractor to pinpoint clusters that contain either many or no object hits. We then show that there are more targets in the clusters with many SExtractor hits than SExtractor finds. We also show that ART clusters together input regions that are dominated by noise that can be used to characterize the noise in an image. The results provided show that unsupervised learning algorithms should not be overlooked for astronomical data analysis. |
|
|
|
|
|
