Importing deep nets from large-scale training systems to embedded processors

Deep nets are becoming pervasive in many desktop and mobile applications; however, running deep nets on small embedded devices remains a challenge. In this talk, Alex Terrazas will describe how to train deep net models on desktop GPU systems and then export them on to small embedded devices like the Raspberry PI.

Some of the challenges include choosing the right implementation on the embedded device (CUDNN, TensorFlow, etc.) and using other tricks that can improve performance (using half-precision parameters). Alex will discuss training and deploying an end-to-end deep net on an embedded device.

About the speaker:

Alex Terrazas, expert in deep learning, data science, geospatial analytics, embedded sensors, computer vision, and virtual reality (VR). Business strategy development and C-level presentation experience. Certified Project Management Professional (PMP). Business experience in 25+ countries.