Decrappifying brain images with deep learning

(University of Texas at Austin, Texas Advanced Computing Center) To understand brain functions, it is necessary to first map how different cells and cell parts interact in three-dimensions. Doing so with existing equipment and methods has been a challenge. Researchers from the Salk Institute developed an approach using deep learning that can speed up brain image microscopy by 16 times. The team trained the deep learning system using data from University of Texas researchers and supercomputers at...