Machine learning methods are extremely powerful but often function as black-box problem solvers, providing improved performance at the expense of clarity. Our work describes a new machine learning approach which translates the strategy of a deep neural network into simple functions that are meaningful and intelligible to the physicist, without sacrificing performance improvements. We apply this approach to benchmark high-energy problems of fat-jet classification and electron identification. In each case, we find simple new observables which provide additional classification power and novel insights into the nature of the problem.
