Data Science Lecture Series, Fall semester, 2020-21
Vangelis Katsikaros, Adzuna "Information technology: trends and the job market", 24 Nov. 2020 @ 12:15-14:00 - MS teams: link
Data Science Lecture Series, Fall semester, 2020-21
Prof. Emmanuel Stefanakis, U. Calgary "Online map service providers: mapping the Globe using tiled maps", 20 Nov. 2020 @ 16:15-18:00 - MS teams: link
Data Science Lecture Series, Fall semester, 2020-21
Prof. Emmanuel Stefanakis, U. Calgary "Online map service providers: mapping the Globe using tiled maps", 20 Nov. 2020 @ 16:15-18:00 - MS teams: link
Data Science Lecture Series, Fall semester, 2020-21
Prof. Dimitris Zissis, U. Aegean & MarineTraffic.com "Maritime data analytics: lessons learnt (& new challenges) from MarineTraffic.com", 19 Nov. 2020 @ 16:15-18:00 - MS teams: link
Diploma Theses Catalogue, 2020
The Data Science Lab offers a list of suggested diploma theses to undergraduate and postgraduate students in subjects relative to the research interests of the laboratory. For more information, contact the person in charge of each diploma thesis. Catalogue
FIRST INTERNATIONAL SUMMER SCHOOL ON DATA SCIENCE FOR MOBILITY
The MASTER Summer School is co-organized by Data Science Lab! Will be nice to see you in Santorini next April! website ABOUT: The objective of the First International Summer School on Data Science for Mobility is to offer to participants both visionary keynote speeches and hands-on mini courses. The keynote speeches are held by leading experts on maritime and aviation domains introducing analysis challenges a large quantities of very complex mobility data generated every day. WHERE: Kastelli Resort, Kamari Village, Santorini, Greece DEADLINE: February 28 2020 For information: master-summer-chairs [at] isti.cnr.it
Compressed communication in Distributed Deep Learning – A Systems perspective
Speaker: Prof. Panos Kalnis, (KAUST) Google Scholar 2020, Feb. 6, 12pm @ UniPi Conference hall (central building, ground floor) Abstract: Network communication is a major bottleneck in large-scale distributed deep learning. To minimize the problem, many compressed communication schemes, in the form of quantization or sparsification, have been proposed. We investigate them from the Computer Systems perspective, under real-life deployments. We identify discrepancies between the theoretical proposals and the actual implementations, and analyze the impact on convergence. We also develop a general framework for compressed communication that supports both TensorFlow and PyTorch, and employ it to implement many existing schemes. We provide a thorough quantitative evaluation over real models and datasets. We demonstrate the effect of the various overheads, such as the computational cost of compression/decompression, on throughput. Finally, we…
(21/11/2019) Panagiotis Tampakis defended his PhD thesis!
Panagiotis Tampakis successfully defended his PhD thesis titled "Big Mobility Data Analytics: Algorithms and Techniques for Efficient Trajectory Clustering". The thesis is available here: thesis; the defense slides are available here: slides . Panagioti, congrats !!