SYSTEM AND METHOD FOR IMPROVING THE PREDICTION ACCURACY OF A NEURAL NETWORK

摘要

A system and method for improving the prediction accuracy of a neural network is proposed. Prediction tasks derived from labeled video data are used to regularize the feature space of the neural network so that it encodes constraints of the physical world while also learning to solve the original task at hand. The videos are generated by instructing humans to perform actions according to predefined labels or descriptions, so that a wide variety of physically relevant motion patterns are available to regularize the network.