Comment Re:See astronomy.net (Score 1) 28
Fair enough, but this is truly unsupervised learning, which has not properly been applied to astro-images before
Comment Re:See astronomy.net (Score 1) 28
No, this is quite distinct from astrometry.net (assume that's what you mean)
Comment Re:Not as difficult as it sounds (Score 1) 28
The problem is that GZ relies on a user base that wants to look at the interesting objects - this will look at all the boring stuff too. Plus, data rates of LSST will be 10s TB/night - this will have to be parsed extremely quickly to find transients. Can't envision crowd sourcing doing that.
Submission + - Astronomers teach a machine to see (ras.org.uk)
Jim Geach writes: A team of astronomers and computer scientists have developed a novel unsupervised machine learning algorithm — a combination of Growing Neural Gas and Hierarchical Clustering — to automatically analyse astronomical images. In effect, the algorithm performs the same task as a human 'eyeballing' an image, automatically identifying and labelling the points of interest. The team is aiming to deploy the algorithm on the next generation of astronomical surveys such as LSST and Euclid, but note that the algorithm could also find application in other fields, such as medical imaging and early disease diagnosis. Team member Dr Jim Geach said
Our aim is to deploy this tool on the next generation of giant imaging surveys where no human, or even group of humans, could closely inspect every piece of data. But this algorithm has a huge number of applications far beyond astronomy, and investigating these applications will be our next step
The results are being presented at the UK National Astronomy Meeting in Wales, and the details of the algorithm are described in this paper http://arxiv.org/abs/1507.0158...
Slashdot Top Deals
"It's when they say 2 + 2 = 5 that I begin to argue." -- Eric Pepke
