I am a DPhil student in the Machine Learning Systems Group at the University of Oxford under the supervision of Nic Lane. I am also a member of Linacre College. I completed my B.Sc in Telecommunication Engineering at TECNUN, University of Navarra (Spain), in 2014 and a M.Sc in Computer Vision at Queen Mary University under the supervision of Prof. Andrea Cavallaro in 2015. Prior to starting my DPhil, I worked as a computer vision engineer at: Hawk-Eye (Sony), where I improved their multi-camera calibration and player tracking software; and at Holition, an award-winning creative studio where I co-designed and implemented augmented reality applications for the fashion retail sector.
My research focuses on making the deep learning algorithms that we love run on very constrain devices. I am primarily focusing on designing neural network architectures that are optimal in scenarios where memory and compute capabilities are limited, as is the case in most IoT devices and wearables. The family of Arm Cortex-M microcontrollers are an example of my target platforms.
I can be reached at —> javier [dot] fernandezmarques [at] cs.ox.ac.uk