Modeling Deep Learning Neural Networks With Denotational Mathematics in UbiHealth Environment

Abstract

Ubiquitous computing environments that are involved in healthcare applications are typically characterized by dynamically changing contexts. The contextual information must be efficiently processed in order to support medical decision making. The ubiquitous computing healthcare ecosystem must be capable of extracting medically valuable characteristics, making precise decisions, and taking medically appropriate actions. In this framework, deep learning networks can be used for data fusion of large and complex sets of information in order to make the appropriate medical diagnoses. The quality of decisions depends on the selection of appropriate network weights, which define a transformation of the given input into a diagnosis. Denotational mathematics provide a promising framework for modeling deep learning networks and adjusting their behavior by adapting their weights for the given input. Furthermore, the fidelity of the network's output can be controlled by applying a regulator to the weights values. The authors show that Denotational Mathematics can serve as a rigorous framework for modeling and controlling deep learning networks, thereby enhancing the quality of medical decision making.