AI Trust

Cignal CTO Presenting at SPIE Defense + Commercial Sensing 2024

Cignal CTO Presenting at SPIE Defense + Commercial Sensing 2024

Cignal's Chief Technology Officer (CTO), Eric Fiterman, will be presenting at the SPIE Defense + Commercial Sensing 2024 event, taking place April 21-25, 2024, at the Gaylord National Resort and Convention Center in National Harbor, Maryland.

Measuring and validating the quality, visual fidelity, and performance of synthetic image data is an advanced and evolving subject. During this conference, Mr. Fiterman will present an overview of various methods and approaches for measuring the visual quality and fidelity of synthetic image data, including established industry standards. He also will discuss how these approaches may be integrated into a continuous integration/continuous delivery (CI/CD) data generation pipeline to monitor and improve data quality and predicted performance for Artificial Intelligence/Machine Learning (AI/ML) use cases.

Mr. Fiterman's presentation, Integrating Synthetic Data Validation and Quality Benchmarks Into a Continuous Integration/Continuous Delivery (CI/CD) Data-Generation Pipeline, is scheduled for the afternoon of Wednesday, April 24, 2024, in National Harbor 7.

In addition to his role as Cignal's CTO, Mr. Fiterman is the lead developer of the Cignal Engine, a synthetic data generation and simulation environment for non-visible spectra. A former Special Agent with the Federal Bureau of Investigation (FBI), he has extensive experience transitioning emerging technologies into classified and national security environments. Mr. Fiterman was the first award recipient of the Department of Defense Advanced Research Projects Agency (DARPA) Cyber Fast Track program and also has served as a Solutions Transfer Consultant for In-Q-Tel, the venture capital arm of the U.S. Intelligence Community. He holds degrees in Computer Science and Electrical Engineering from the University of Maryland and has strong interests in GPU computing, open source software, simulation, and reinforcement learning.