News

  • The Rawfie Project

    RAWFIE (Road-, Air-, and Water- based Future Internet Experimentation) is a project funded by the European Commission (Horizon H2020 program) under the Future Internet Research Experimentation (FIRE+) initiative that aims at providing research facilities for Internet of Things (IoT) devices. The DMML team has been involved in the RAWFIE project since early 2015 and delivered their final contributions in June 2019 as the the project ended. The members of the team invested in the project, Jason and Lionel, were responsible for the design and development of the platform's data analysis tools, enabling experimenters to apply machine learning algorithms on data collected via the platform's unmanned devices. Read more
  • Talk on Earthquake prediction research by Prof. George C. Anagnostopoulos

    On Friday, the 8th of November 2019, we have the pleasure of hosting Prof. George C. Anagnostopoulos, who will present his work on: “Data Analysis and Interpretation of Electromagnetic disturbances detected by Low Earth Orbit (LEO) satellites before Earthquakes (EQs): Perspectives for the EQ prediction research.” Read more
  • Frantzeska at Swiss Machine Learning Day on 13Nov2019

    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 Swiss Machine Learning Day held at the SwissTech Convention Center in the EPFL campus on Wednesday November 13th, 2019. Come and check it out! Read more
  • Paper about LoRaWAN localization presented in WPNC

    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. Read more
  • TechLunch – meeting industry

    In cooperation with the Geneva Creativity Center we're organizing on 22nd October 2019 a TechLunch to  discuss with companies in the Geneva region what machine learning can bring to them. It is an occasion for anybody interested in applying machine learning and/or data analytics methods in more general to discover what we do and can offer in this respect, to learn from our existing industrial partners about their experience in collaborating with us, and to exchange views and insights in a relaxed and open atmosphere during a lunch break. The meeting will be held in the building of Sciences III, Université de Genève, Boulevard d'Yvoy 4 from 12pm-14pm. To attend, please register at the CGG web sight by 17th October 2019. Read more
  • Paper presentation in IPIN 2019

    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 to follow the latest advancements of the field and discuss with very knowledgable and exciting people. Over the last couple of years the IPIN conference has expanded its call for papers to subjects concerning outdoor positioning, often getting their inspiration from methods that are well established indoors. In our recent blog post Outdoor positioning in the IoT world, we have presented an introductory description of such scenarios. It has been a truly great experience and we are looking forward to attending IPIN 2020, in Beijing, China. Read more
  • Welcome to Nikos

    We have got a new PhD member. Nikos Kostagiolas has joined us in the beginning of September. His plan is to become one of our reinforcement learning wizards. Working on models of human locomotion within our project on pathological gait modelling will certainly provide him with ample opportunity to sharpen his skills. Welcome Nikos! Read more
  • Talk by prof. Byeng Dong YOUN

    In developing our collaborations with experts and scholars around the globe, we were happy to welcome Dr. Byeng Dong YOUN, Professor of Mechanical and Aerospace Engineering at Seoul National University (SNU), the founder and CEO of OnePredict Inc. (onepredict.com), and the President of the Korean Society of Prognostics and Health Management (PHM). Prof. Youn presented his talk on Industry AI based Machine Intelligences for Industrial Digitalization and we discussed the challenges related to applying machine learning techniques in industrial monitoring. Read more
  • Variational saccading

    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! Read more
  • ML research on the move

    Though ML labs may seem to outsiders as rather nerdy isolated groups, it is not our case! We are on the move, visiting and welcoming ML researchers, sometimes near and sometimes further away. Discussing, collaborating, making friends, having fun! Read more