Add us to yourGoogle favoritesA neural network “trained” in the analysis of gravitational lenses has led to the discovery of 56 new lenses across a small section of the sky, promising many more discoveries ahead. A team of astronomers from the universities of Groningen, Naples, and Bonn developed a method to accurately analyze the complex distortions of space-time, the famous gravitational lenses. For this study, the astronomers trained the neural network using millions of homemade images of gravitational lenses. Initially, the neural network identified 761 potential candidates. These 56 new lenses still need to be confirmed by “visual” telescopes, such as the Hubble Space Telescope.