METHOD AND SYSTEM FOR TRAINING A NEURAL NETWORK

摘要

A method and system (20) for training a neural network (95) is disclosed herein. A processor (41) is configured to train a neural network to learn to generate a plurality of sub-concept outputs from a first plurality of inputs (80) of the plurality of digital input signals. The processor (41) is also configured to use the plurality of sub- concept outputs as a plurality of target outputs for a plurality of top-level inputs of the plurality of digital input signals.