"Brant Robertson noted, 'There's been this evolution [from] looking at a few objects, to doing CPU-based analyses on large scales of the data set, to then doing GPU-accelerated versions of those same analyses.'"
"Robertson and Ryan Hausen developed Morpheus, a deep learning model that analyzes large data sets to identify galaxies, revealing unexpected findings about disc galaxies."
"Morpheus is evolving as Robertson transitions its architecture from convolutional neural networks to transformers, reflecting advancements in AI technology."
NASA's Nancy Grace Roman space telescope is set to launch in September 2026, ahead of schedule. It will provide astronomers with 20,000 terabytes of data. This complements the 57 gigabytes of imagery from the James Webb Space Telescope and the Vera C. Rubin Observatory's expected 20 terabytes of nightly data. The Hubble Space Telescope, in comparison, delivers only 1 to 2 gigabytes daily. Astronomers are increasingly using GPUs to analyze this vast data, with advancements like the Morpheus deep learning model aiding in galaxy identification.
Read at TechCrunch
Unable to calculate read time
Collection
[
|
...
]