Deep Learning With MXNET On Video: Ring & Xbox video demos

Abstract:
This talk will go over using MXNET on video streams such as security footage from Ring, or live XBOX video data to perform inference and indexing. This can be used to classify video events, detect anomalies in normal behavior, and search. This talk will focus on using FFMPEG for feeding MXNET models for fast inference throughput and performance. This talk will also discuss the difference between frame level inference, and frame buffer inference (comprehending a temporal video event).

Speaker info:
Ben Taylor has over 14 years of machine learning experience. He has worked for five years in the semiconductor industry for Intel and Micron in photolithography, process control, and yield prediction. He has also worked as a Wall Street quant building sentiment stock models for a hedge fund trading the S&P 1500 on the news content on a 600 GPU cluster. Ben left finance and semiconductor to work for a Sequoia-backed start-up called HireVue in 2013 and lead their machine learning efforts around digital interview prediction and adverse impact mitigation. Ben works full-time now as a co-founder for Ziff.ai and uses deep-learning on audio and video data for a variety of industries.