From Dark Matter to Galaxies with Convolutional Networks · HackerPapers discussions

From Dark Matter to Galaxies with Convolutional Networks — mentioned by cxw

Wed, 01 Jul 2020 04:09:46 GMT

I also work in computer vision (for biological sciences). I use deep convnets every day, and certainly they are increasingly central in biology (https://arxiv.org/abs/1611.00421), proteomics (https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3837439/, https://deepmind.com/blog/article/AlphaFold-Using-AI-for-sci...), astronomy (https://arxiv.org/abs/1902.05965), chemistry (https://www.nature.com/articles/s42254-019-0086-7, https://pubs.rsc.org/en/content/articlelanding/2019/sc/c8sc0...), many other sciences. I think it's great, they're enabling progress in lots of really tough scientific problems.…

Paper and discussion history. A mention is not an endorsement.

From Dark Matter to Galaxies with Convolutional Networks — mentioned by ArtWomb

Mon, 13 Jan 2020 14:01:33 GMT

As science historian John Horgan noted in The End of Science the parallel in physics is with academic humanities departments becoming mired in "irony" The End of (one type of) Physics, and the Rise of the Machines https://www.math.columbia.edu/~woit/wordpress/?p=10680 Seems there are two possible outcomes. The deluge of data leads to better correlation which smooths over the flaws in current models. And corrects errors with some minor fudge factor that contains no further significance. From Dark Matter to Galaxies with Convolutional Networks https://arxiv.org/abs/1902.05965 Or something…

Paper and discussion history. A mention is not an endorsement.