A METHOD FOR BUILDING A DEEP LATENT FEATURE EXTRACTOR FOR INDUSTRIAL SENSOR DATA

摘要

The present invention relates to a method of and a system for building a latent feature extractor as well as a neural network (NN) comprising latent feature extractor built by said method and/or with said system. The method comprises providing non-uniform training data for a multitude of tasks and optimising parameters θ of a neural network (NN) of the latent feature extractor based on the multitude of tasks.