What is Geometric Unified Learning?

Geometric Unified Learning, or GUL, is a proprietary advanced machine-learning technology that models the human body like a dynamic system. It only needs 2% of

characteristic data and automatically de-identifies patients. GUL differs from other models because it integrates big data machine learning with differential geometry, a novel approach developed by Dasion’s founder.

GUL excels over other machine-learning solutions because it uses reinforcement learning and a control loop so the system does not need retraining. Instead, it gets better and better every time a doctor uses it.

The Geometric Unified Learning System at Dasion’s core is what makes it a true clinical decision-making tool. It’s the only machine-learning technology that can:

1. Create geometric data patterns as essential biomarkers. These patterns can be detected by GUL in voice data.
2. Simultaneously search and learn, pulling out similar patient cases and documents, and then choose optimal data features and machine-learning methods.
3. Fuse different types of data and integrate different machine-learning results.

Dr. Weiqing Gu: Dasion’s Founder and Inventor of GUL

Dr. Weiqing Gu is the founder and CEO of Dasion. After attending college at the age of 15, she received a Master’s and PhD 1 in Mathematics from the University of Pennsylvania, as well as a Master’s in Computer and Information Science, also from the University of Pennsylvania.

Her accomplishments and accolades include the following:

• Held titles of McAlister Professor 2 and Clinic Director of the Mathematics Department at Harvey Mudd College
• Served as Program Director for the National Science Foundation (NSF), leading the big-data-challenge team and collaborating with the U.S. Navy and the Defense Threat Reduction Agency (DTRA)
• Selected by the American Mathematical Society to present her NSF research to the 110 th U.S. Congress
• Featured in Forbes 3 for her COVID-19: Data Analytics/Machine Learning course at Harvey Mudd
• Recognized for exceptional performance by the U.S. Navy for her work on unmanned aerial vehicles (UAV), radar, and hyperspectral image data
• Served as Principal Investigator for the U.S Navy, designing an anomaly- detection system for multiple unmanned aerial systems
• Awarded Small Business Innovation Research Phase I grant from the NSF in 2021 4
• Awarded Small Business Innovation Research Phase II grant from the NSF for $999,998 through 2026 5