Using Geometric Unified Digital Biomarkers to Detect Neurological Diseases

W. Gu
Dasion (Data-to-Decision) Corporation,
United States

Keywords: digital biomarkers, neurological diseases, machine learning, big data analytics


This talk will discuss the use of Geometric Unified Learning (GUL) technology to detect neurological diseases. GUL is a technology consisting of reusable building blocks that overcomes several disadvantages of traditional deep learning methods. It brings increased value to end-users by saving time and resources in data processing, fitting data before it is input to a deep neural network to avoid overfitting, providing transparency and trustworthy solutions that can easily be understood by data-to-decision makers, making data analysis interesting for software developers, scientists and engineers outside of the machine learning field, producing flexible, robust and agile solutions for debugging, and saving money. This Small Business Innovation Research (SBIR) Phase I project addresses several technical challenges in deep learning by using GUL to create appropriate local coordinate systems, Riemannian metrics, transformations, and geodesics to identify data invariants and intrinsic patterns. The GUL tools have capabilities of vectorizing data, compressing data, searching and learning simultaneously, with highly interpretable results. When the technology makes predictions it will show the user exactly which data points are responsible for those predictions.