Plenary Talk: Topologically-Informed Data Driven Analytics & Fusion
Dr. Paul T. Schrader, AFRL/RF will present a plenary talk on Autonomous Applications of Topologically-Informed Data Driven Analytics & Fusion.
ABSTRACT: This decade's 'digital wild' is inundated with high rate, voluminous combinations of physics- and human-based data. The challenge is further exacerbated by rapidly accelerating autonomous architectures lacking explainability, compromised/poisoned heterogeneous data, and managing denied/degraded/intermittent/low-bandwidth environments. These and other prohibitive symptoms weaken user certainty while concurrently increasing compute complexities and reducing edge processing compatibility, resulting in failed support of (near) real-time decision speed. Addressing these challenges motivates rigorous scientific creativity through multi-disciplinary approaches, particularly leveraging the rich mathematical properties of a network's upstream data and their fused aggregates. Computational and algebraic topology implemented by topological data analysis (TDA), both classical and emerging, provide access to these properties and a path to modality/model agnostic fusion. This talk exhibits one such ongoing success, an efficient and scalable TDA Machine Learning algorithm (TDAML – US Patent Pending 18645545) and examines several case studies recently developed including applications in surveillance, time-series forecasting, data assurance, and materials/systems inspection. After a brief overview introducing TDA, an overarching dissection of the TDAML along with a survey of its object detection/classification studies and emerging implementations (e.g., adaptive multimodal fusion, OOD detection/decontamination, explainability in black-box transformers, user certainty quantification, surrogate arithmetic approaches to TDAML to resolve compute complexity trade-offs for high-rate/real-time data analytics, etc.) are presented. Finally, future directions for the TDAML and other TDA-informed methodologies are discussed leveraging arbitrary physics- and human-based data analytics/fusion towards reliable and deployable mission driven situational/state/systems/material/cyber awareness.
BIO: Dr. Schrader is a Senior Research Mathematician for the Air Force Research Laboratory's Information & Spectrum Warfare Directorate (AFRL/RF), Rome, NY location. A non-traditional student originally working for years in the wholesale distribution, logistics and welded fabrication industries, he received his BA (2011) and MS (2013) in mathematics from Cleveland State University where he began his studies in topological data analysis (TDA). In 2018 he obtained a PhD in mathematics from Bowling Green State University specializing in non-associative algebras and monoidal/tensor/modular categories. Prior to the AFRL/RF he was a tenure track Assistant Professor of Mathematics at Southern Arkansas University from 2018-2022. With multiple publications and patents pending in a variety of TDA, mathematics, math education, and AI/ML based subjects, his research includes the applications of TDA and other novel mathematical approaches to modality/model agnostic, edge amenable data driven information fusion autonomy in: target recognition and continuous custody, tactical/strategic terrestrial/aerial/maritime/cislunar sensing environments, systems/materials/high-rate health monitoring and situational/state/space domain awareness, battle/natural disaster damage assessment, network resiliency and data assurance, human-machine interfacing, and general dynamic data-driven applications systems/phenomena.
To schedule interpreter and/or services for this event, please use https://myaccess.rit.edu
Event Snapshot
When and Where
Who
Open to the Public
| Cost | FREE |
Interpreter Requested?
No