One of the things that makes the weather so dangerous is that it's so hard to predict. Tornadoes, hail, high winds and flash floods cause billions of dollars worth of property damage, and injure or kill hundreds of people in the United States each year. Knowing when storms may strike can save lives, and property. Our guest is part of a team at the National Center for Atmospheric Research that's doing just that. We spoke with David John Gagne, a postdoctoral fellow at the National Center for Atmospheric Research about his work with deep learning at the GPU Technology Conference in Silicon Valley this week.