Focused full-time on developing, testing, and scaling field-capable Machine Learning models for medical image classification used for read prioritization, triage, and workflow.
This...more is not just with academic benchmarks – we use real patient data and have built a scalable, distributed processing environment to support a 20TB+ training dataset on a massive local NVIDIA training grid we maintain.
Built entire investment analytics architecture, technology platform, and team from zero to a turnkey, fully automated system covering 96% of the firm's $240B portfolio. Built...more technology + team for the firm's valuations service. Architected firm's scenario and stress testing platform for complex scenario runs using distributed computation farm.
DeepJams - AI Generated Music w/ Genre Style Transfer
You can start using our application here. Just follow the two easy steps below or see the usage demo video on the right. Step 1) upload an MP3 file, much… · More like this one (we all happen to be huge fans of Sandstorm) Your browser does not support the audio element.
Our areas of interest are diagnostic imaging and hospital workflows. We took the most interesting and bleeding-edge health tech 2.0 ideas, spec'd and… · More prototyped them out, and are working with hospitals to actually use them on the field.
It is simple...I can make things happen. I can work with senior management as well as coach entry level employees, get my hands dirty, prototype rapidly. I can manage expectations, drive deliveries and ship. So with all that, I can make things happen; and I have, over and over with many teams.
Lead efforts to build medical image driven diagnostic classifier (using CNN based deep learning on Tensorflow) for rapid case triaging trained against actual medical data (20TB+).
Helped lead the massive, global, highly-visible, and viciously political restructuring and unwinding of AIG Investments' derivatives systems, processes, operations, and book restructuring in 2008 and 2009.