Iterative neural network training using quality assurance neural network

Abstract

In some implementations initially training a first neural network includes inputting the training inputs and corresponding training labels into the first neural network to produce output labels, comparing the output labels to the corresponding training labels using a second neural network that learns and applies a comparison metric, and adjusting parameters of the first neural network based on the comparing. The device then inputs additional inputs into the first neural network to produce additional output labels and corresponding confidence values from the second neural network. The device selects, based on the confidence values, an automatically-labeled training set of data including a subset of the additional inputs and a corresponding subset of the additional output labels. During a second training stage, the device trains the first neural network and the second neural network using the automatically-labeled training set of data.