Ph.D. student at DASYA lab @ IT University of Copenhagen focusing on machine learning on resource-constrained devices, on-satellite ML and performance analysis.
This Sunday, @deem_workshop (@SIGMODConf), @robertbayer_ will present his work on determining the right edge device to deploy on a small satellite for data-intensive Earth observation applications. The satellite built based on his results is now in Space.
@dasyaITU@ITUkbh
RAD team will be at EuroSys! Ties Robroek & @AslEhsan will present our analysis of GPU collocation methods at @euromlsys, @robertbayer_ will present his PhD plan for ML at the Edge at Doctoral Workshop, and I will give a talk on performance analysis for deep learning at ESwML.
I am happy to share that I have won the prize for the best master thesis in computer science in 2023 in Denmark! Huge thank you to my supervisor @pinartozun , and @IDAdk and @DanskIndustri .
We are very interested in Machine Learning on *extremely* small devices - therefore announcing:
Tech Tease Workshop: Machine Learning on Tiny Devices, organized by @dasyaITU & @nvidia Denmark
June 7, 2023, ITU
https://t.co/SqpyjSkKtW
Observing the interaction of deep learning with modern hardware is crucial to prevent hardware underutilization. @AslEhsan will be presenting our work on pros/cons of profiling & monitoring tools on NVIDIA GPUs to aid such observations at @euromlsys on Monday.
@dasyaITU
After a lot of delays, today we saw the successful launch of the SpaceX's Transporter-7 mission and the subsequent separation of the Vigoride-6 carrying our DISCO1 satellite!
https://t.co/T8mcj1bBW9
In two weeks, the DISCO1 will deploy and the LEOP begins!
More info on RAD-day (Feb 13, 11am-3pm CET) talks is now available at https://t.co/MtnsajBsbF.
Thanks Rob van der Goot @robvanderg, Zoi Kaoudi, Matthias Boehm @matthiasboehm7, Florina Ciorba @cflorina, Luca Maria Aiello @lajello, Oana Balmau @oanabalmau for being part of this.
@hamesh__p@tpcbenchmarks Thank you for the great work you have done on the benchmark! I think today has shown us that the benchmark is a great and needed addition.
Happy to announce that I am going to be giving a talk on our work on "TPCxAI on NVIDIA Jetson" in Sydney at TPCTC co-located with @VLDBconf. This was my first attempt at academic writing, and I now feel encouraged to continue on this path. 1/2
Happy to announce that our performance characterization study of NVIDIA Jetsons using TPCx-AI got accepted to TPCTC (https://t.co/7KlCdELHEk) co-located with @VLDBconf.
Big congrats to @robertbayer_ and Jon Voigt Tøttrup, who did the hard work.
@dasyaITU@ITUkbh@daphne_eu