Our joint work with University of Lincoln, UK, University of Aberdeen and Chalmers University of Technology on using machine learning techniques for the analysis of nuclear plant data in the frequency domain has just been published on the Annals of Nuclear Energy! authors.elsevier.com/sd/article/S03…

ΚΑΛΛΙΠΟΣ+, 1η Βιβλιοπαρουσίαση dlvr.it/SX2SxN

Initiatives for the integration of Ukrainian refugee students into higher education institutions dlvr.it/SX55sw

Our joint work with University of Lincoln, UK, University of Aberdeen and PSI Paul Scherrer Institut on using machine learning techniques for the analysis of nuclear plant data in the time domain has just been published on the Annals of Nuclear Energy! authors.elsevier.com/sd/article/S03…

The work of lab members Tasos Papagiannis, George Alexandridis and Andreas Stafylopatis on "State similarity based Rapid Action Value Estimation for general game playing MCTS agents" has just been published on the proceedings of the FDG 2023 Conference conference. dl.acm.org/doi/abs/10.114…

Computer Science Talks, 9 January 2023, 16:00-20:00, Conference Hall, NTUA Administration Building dlvr.it/SgQ3QZ

Lab members’ George Alexandridis work on Online Batch Selection for Enhanced Generalization in Imbalanced Datasets has just been published on the Deep Neural Networks and Optimization Algorithms SI of Algorithms MDPI #deeplearning #machinelearning mdpi.com/1999-4893/16/2…

The Innovation Hub for Digital Governance #GRdigiGOVinnoHUB kicks off! 16 public bodies and R&E institutions join forces to develop innovative digital solutions in Public Administration, with #AI,#Blockchain,#IoT,#Cloud, #HPC, #opensoftware,#opendata,#openstandards.

"Εχουμε μπροστά μας μεγάλες προκλήσεις για την εισαγωγή και χρήση των νέων τεχνολογιών στην ψηφιακή εποχή της Δημόσιας Διοίκησης, με επίκεντρο και προς όφελος των συμπολιτών μας". Καθ. Στέφανος Κόλλιας, Πρόεδρος #ΕΔΥΤΕ, εναρκτήρια συνάντηση #GRdigiGOVinnoHUB

Prof. Stefanos Kollias and PhD's Anastasis Arsenos and Paris Theofilou are among the organizing committee of the AI-MIA-COV19D workshop to be held in conjunction with IEEE ICASSP 2023 in Rhodes Island, Greece, 4 – 9 June, 2023 #machinelearning #covid19 #ai mlearn.lincoln.ac.uk/ICASSP-2023-AI…

📝Want to use a counterfactual editor but don't know if its edits are truly minimal? Measuring inconsistency may help! Our paper “Counterfactuals of Counterfactuals: a back-translation-inspired approach to analyse counterfactual editors”, delves deep into this. #ACL2023 Findings

We introduce a novel metric which uses iterative feedback steps to evaluate the inconsistency of editors!

🔎 The behavior and outputs of counterfactual editors varies a lot, but there is no universal ground truth for counterfactual edits. As such it is hard to tell what would be the optimal counterfactual. 🔍 We propose a using previous editor outputs as ground truth proxies.

We compare three editors on two datasets covering different types of use cases (adversarial and counterfactual, black and white box, with or without LLMs), gaining useful insights on the editors’ behavior.

Some insights : MiCE achieves lowest minimality but tends to leave remnant text spans, as indicated in the example below. This observation is also reflected in the inc@n: there is a higher value of inc@n when n is even indicating that it is easier to return to the original class.

You can checkout the paper here: arxiv.org/abs/2305.17055 or talk to us in person at #ACL2023 (come to our spotlight talk too). w/ Eddie Dervakos, Orfeas M, Chryssa Zerva and G Stamou AILS_NTUA

An article discussing data augmentation techniques for Reinforcement Learning agents’ in Game AI by PhD candidate Tasos Papagiannis, Dr. George Alexandridis and Professor Andreas Stafylopatis has just been published on the Multi-Agent Systems SI of Applied Sciences MDPI mdpi.com/2620668

Our joint work with DeepLab on Self-Supervised Learning for Visual Relationship Detection through Masked Bounding Box Reconstruction has just been presented at WACV as a poster! #WACV2024 #vrd #deeplearning openaccess.thecvf.com/content/WACV20…

I have just presented our joint work with Olympia Odos & Extrabit on Deep Recurrent Neural Networks for Highway Traffic Flow Prediction at Toll Stations at the 2024 IEEE World Forum on Public Safety Technology (WF-PST) conference. IEEE Public Safety Technology Initiative #WFPST AILS_NTUA

Panagiotis Kouris, George Alexandridis and Andreas Stafylopatis work on text summarization based on semantic graphs has just been published open access by the Journal of Big Data by Springer Open! link.springer.com/10.1186/s40537…