At this week’s google FL workshop, we are announcing our open source tool that makes it easier to devise and evaluate FL algorithms under real-world conditions: http://flower.dev. The paper can be found on arxiv.
Shangzhe Wu presented their work on “Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild” which was awarded Best Paper at CVPR 2020!
Miltos Allamanis visited on 11 February 2020 and gave a talk on Analyzing Source Code using Graph Neural Networks and Natural Language.
Andreas Soleiman visited from Uppsala University to present his work on battery-free backscatter systems: “Towards Sustainable Widespread Sensing”.
Peter Blacker, from the University of Surrey, visited to present his talk on “Deep Learning in Space”.
David Kotz, from Dartmouth College, visited to present his talk on “Secure, Intentional Communications with Mobile Devices”.
Tao Gu, from RMIT, visited to present their talk on “Surviving Screen-off Battery through Out-of-Band Wi-Fi Communication”.
Edgar Liberis helped to organise a workshop and hackathon using Intel’s Neural Compute Stick (NCS) accelerator.
Paul Whatmough visited on 7 March and gave a talk on Algorithm-Hardware Co-Design for Energy-Efficient Neural Network Inference.
Petar Veličković visited our group and spoke on the intersection of adversarial learning and graphs.
Our paper, “A Systematic Study of Binary Neural Networks’ Optimisation”, was accepted at ICLR 2019.
subscribe via RSS