A committee machine is a model architecture that combines the outputs of multiple expert models or neural networks into a single response. The combined decision is intended to be more accurate or robust than the output of any individual expert.
A type of artificial neural network using a divide and conquer strategy in which the responses of multiple neural networks (experts) are combined into a single response. The combined response of the committee machine is supposed to be superior to those of its constituent experts. Compare ensembles of classifiers.