We develop a first line of attack for solving programming competition-style problems from input-output examples using deep learning. The approach is to train a neural network to predict properties of the program that generated the outputs from the inputs. We use the neural network’s predictions to augment search techniques from the programming languages community, including enumerative search a...

The entire experiment revolves around the research hypothesis [1] (H1) and the null hypothesis [2] (H0), so making a mistake here could ruin the whole design [3]. Needless to say, it can all be a little intimidating, and many students find this to be the most difficult stage of the scientific method [4]. In fact, it is not as difficult as it looks, and if you have followed the steps of the scie...