HuMaLearn

"Distributed Systems - The next level" Francqui Chair with Prof. Schahram Dustdar @dustdar next week (March 29-31) at @UNamurCSFaculty of @UNamur. Event online, free, but registration is required. @digitalwallonia @AdN_Wallonie @infopoletic @UWE_asbl unamur.be/info/chaire-fr…

An article about the @CSLabsNamur 📰 #_ga=2.201446931.307765194.1648202627-449866463.1635715367" target="_blank" rel="nofollow noopener">lesoir.be/432024/article…

on ML model interpretability and explainability in the context of private and public decision making. It then explains how those legal requirements can be implemented into machine-learning models and concludes with a call for more inter-disciplinary research on explainability.

"Legal requirements on explainability in machine learning" - DL and black-box models are more and more popular today. Yet, they may not be accepted ethically or legally because of their lack of explainability. This paper presents the increasing number of legal requirements...

Interested on the impact of #law on #explainability in #MachineLearning and vice versa? 🧑‍⚖️+🖥️=🥰 Check out our paper with Adrien Bibal, @LognoulMichael, Alexandre de Streel and @benoitfrenay. #ML #GDPR @UNamurCSFaculty @CRIDS_UNamur @UNamur link.springer.com/article/10.100…

We show how the Particle-Mesh algorithm can be directly transposed in the particular case of t-SNE by first computing a potential in space and deriving from it the movements of points in the low dimensional space. By using FFTs, this leads to a significant speedup of t-SNE. (3/3)

“Accelerating t-SNE using Fast Fourier Transforms and the Particle-Mesh Algorithm from Physics” aims to close the gap between t-SNE and the Particle-Mesh algorithm used to solve the N-body problem in physics when N is large. (2/3)

We are happy to present you our paper about accelerating t-SNE with Particle-Mesh at #IJCNN with @ValDelch, Alexandre Mayer, Adrien Bibal and @benoitfrenay at @UNamurCSFaculty thanks to @frsFNRS and EOS VeriLearn project. #dataviz #DataScience #ML ieeexplore.ieee.org/document/95343… (1/3)

"L’IA au service de la Neurologie" avec @benoitfrenay, des collègues de la Faculté de Médecine de l'@UNamur et des spécialistes de @CanonMedicalEU. Merci au @cdsunamur ! @UNamurCSFaculty @AdN_Wallonie @digitalwallonia #SDC2022 #EUAIWEEK @ai4_belgium youtube.com/watch?v=1QBsRM…

We define a flexible taxonomy of constraints applied to decision trees and methods for their treatment in the literature. Then, we benchmark state-of-the art depth-constrained decision tree learners with respect to predictive accuracy and computational time. (3/3)

"Constraint Enforcement on Decision Trees: a Survey" funded by @frsFNRS @FWOVlaanderen EOS VeriLearn project eos.cs.kuleuven.be/content/home @lucderaedt @patrick_heymans @pyschobbens @GPerrouin @jessejdavis1 @benoitfrenay @HendrikBlockeel is the first survey on constraints on DTs. (2/3)

We are glad to see our #openaccess survey published on ACM Computing Surveys about constraint enforcement on decision trees with @genanfack, @pleupi22 and @benoitfrenay at @UNamurCSFaculty thanks to @frsFNRS. #ACMSurvey #DecisionTree #Constraints dl.acm.org/doi/abs/10.114… (1/3)

The results suggest that state-of-the-art models for action recognition still lack sufficient internal representation power to capture the high level of variations of a sign language. (6/n)

Baseline SLR experiments are conducted on LSFB-ISOL and the reached accuracy measures are compared with those obtained on previous datasets. (5/n)

We are proud to introduce two new Sign Language datasets, some of the largest available in terms of video length. Also battery-included: Python interface available! #IJCNN #ComputerVision #LSFB @jefidev @anthonycleve @UNamurCSFaculty @UNamur ieeexplore.ieee.org/abstract/docum… (1/n)