Los Alamos National Laboratory

According to the lottery ticket hypothesis, the bigger the neural network, the more likely some of its weights are initialized to values that are well suited to learning to perform the task at hand. But just how big does it need to be?

Geologists call them slow slips: deep, low-frequency earthquakes that can last a month but have little effect on the surface. A model trained to predict such events could help with forecasting potentially catastrophic quakes.