Application-specific quality metrics for the assessment of data for deep learning from large datasets

Abstract

Application-specific quality metrics support getting suitable data from large databases to pre-train deep neural networks or getting good statistical measures. Especially when using high-dimensional or multimodal sensor data from industrial processes the small amount of training examples from each device or plant must be supplemented by additional data. We present a system for the definition of application-specific metrics in a model composed of statistical functions and neural networks. Further, we introduce a business model for using this system for the interaction of data providers with their customers. In order to obtain suitable data, the user sends his request to the data provider in the form of a quality metric model and gets back the best fitted data. Our system helps the user to define the model through examples and by setting the model parameters through genetic algorithms.