Tag Archives: conference
A couple of months ago Jason Ramapuram interned in Apple Machine Learning Research. Among other things, he worked with Russ Webb on a novel method allowing for the use of simple non-differentiable functions at intermediary layers of deep neural networks. … Continue reading
In addition to being a busy mother of a 2 year old, in her research, Frantzseska Lavda has been investigating how to improve the generative properties of variational autoencoders. She will present her ideas in a poster session of the … Continue reading
Our paper "A Reproducible Comparison of RSSI Fingerprinting Localization Methods Using LoRaWAN" was presented by Grigorios Anagnostopoulos, in the 16th IEEE Workshop on Positioning, Navigation and Communications (WPNC 2019), in Bremen, Germany. The scope of the WPNC contributions this year ranged from IoT and 5G positioning, to autonomous car localisation using LiDAR descriptors. The strive for more transparent and reproducible research in the field, which Greg promotes in his paper, was well appreciated by the community.
Grigorios Anagnostopoulos presented the paper "A Reproducible Analysis of RSSI Fingerprinting for Outdoor Localization Using Sigfox: Preprocessing and Hyperparameter Tuning" in the 10th edition of the Indoor Positioning and Indoor Navigation (IPIN) conference. Attending this conference offered a great opportunity … Continue reading
Ever tried to train a deep neural network over high resolution images taken by modern smartphone cameras or smart devices? The memory and inferential costs when working with inputs of such large dimensions (e.g. 4000x3000) increase rapidly and often prohibitively. Jason Ramapuram proposes a solution in his new paper "Variational Saccading: Efficient Inference for Large Resolution Images". He will present his idea at the BMVC conference in September this year but you don't have to wait, check out the preprint!
AISTATS 2019 is well under way and Lionel Blonde is there to present his work on Sample-Efficient Imitation Learning via Generative Adversarial Nets. You can check his poster Th79 at the poster session tomorrow (Thursday, April 18, 13h30-16h30). He will be happy to explain how he improves upon GAIL by reducing the sample complexity by orders of magnitude. Go and speak to him!