Brian Goodwin

Chief Technology Officer at RAIC Labs

Before joining Synthetaic, Brian was the Principal Data Scientist at a cloud implementation firm with an AI focus. Brian was responsible for architecting and deploying enterprise big data cloud-based AI solutions across many industries. Since he did all of this in the Azure cloud framework, Brian works in close collaboration with Microsoft senior technical staff. Prior to his industry work, Brian earned his PhD with a focus in computational neuroscience from Marquette University (MU) with specialization in medical imaging, signal processing, machine-learning (AI), and high-performance computing. During his postdoctoral studies at Medical College of Wisconsin (MCW), he used computational and AI methods to characterize injury mechanisms in the event of a roadside bombs (IEDs) in combat zones. Using many disparate sensing modalities along with machine-learning models, he worked to characterize the dynamic response of the spine in a seated soldier when exposed to impacts that resemble those from underbody blasts in armored vehicles. This characterization was instrumental in the design of an anthropomorphic test device (ATD, or crash-test-dummy) for use in armored vehicle design. He has built many complex predictive models, some of which have been published, or even become MSFT case studies

Location

Milwaukee, United States

Links

Previous companies


Org chart


Teams


Offices

This person is not in any offices


RAIC Labs

1 followers

We've rebranded, Synthetaic is now RAIC Labs! Quickly derive insights from large, unlabeled geospatial, video, and image datasets without time-intensive human labeling or pre-built models. Rapid Automatic Image Categorization (RAIC) is an unbiased tool that meets users’ ever-changing analytic demands for their perpetually evolving datasets, in an unrivaled timeline. RAIC enables users to find and classify anything in minutes, not months, without labeled data. Simply provide a single example object image and RAIC will find similar objects in your unlabeled dataset and return contextually-related results. You can then improve the AI by identifying the best results through an intuitive human nudge tool. From there, you can run inference jobs and turn results into insights using dashboarding tools or existing analytics platforms.