Talk by Reza Zadeh, Computer Vision @Matroid (CEO) and Machine Learning @ Stanford (Adjunct Professor)
Abstract:
We present an overview of Computer Vision deployments on Matroid, detailing customized visual search and stream monitoring to a large number of users. We demonstrate how to build computer vision neural network models in the browser. Along the way, we explain how Matroid creates, trains, and visualizes TensorFlow models, which are provided at scale to monitor video streams and visually search large collections of media. We use these models to solve challenging problems: The Princeton ModelNet Challenge, and pushing the boundaries of medicine with improved glaucoma detection using Computer Vision.
Everyone is welcome!