Mathematics – Logic
Scientific paper
Jan 2010
adsabs.harvard.edu/cgi-bin/nph-data_query?bibcode=2010aas...21543812m&link_type=abstract
American Astronomical Society, AAS Meeting #215, #438.12; Bulletin of the American Astronomical Society, Vol. 42, p.394
Mathematics
Logic
Scientific paper
Supervised Artificial Neural Networks (ANN) have been used previously to predict the morphological classification of galaxies. However, this work has been limited by the lack of both large training and testing sets. By incorporating the morphological classifications of galaxies from SDSS DR7 provided by Galaxy Zoo there exists a unique opportunity for further the development of this techinique. The Galaxy Zoo project, established in 2007 (Lintott 2008), is a citizen science initiative with over 230,000 participants that works to understand galaxies and galaxy evolution in the nearby universe using images from the SDSS. Galaxy Zoo's morphological classifications have not only provided us a large and highly accurate data set, but also provide a classification confidence for each galaxy. We present an improved ANN technique which has taken advantage of not only the large data set, but also the classification confidence by implementing a fuzzy-logic based ANN.
Lintott Chris
Miller Scott
No associations
LandOfFree
Galaxy Zoo, Training Artificial Neural Networks with Fuzzy Logic does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Galaxy Zoo, Training Artificial Neural Networks with Fuzzy Logic, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Galaxy Zoo, Training Artificial Neural Networks with Fuzzy Logic will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-968799