Zobrazeno 1 - 10
of 34
pro vyhledávání: '"Lemberger, Pirmin"'
One well motivated explanation method for classifiers leverages counterfactuals which are hypothetical events identical to real observations in all aspects except for one feature. Constructing such counterfactual poses specific challenges for texts,
Externí odkaz:
http://arxiv.org/abs/2402.00711
Adaptive learning is an area of educational technology that consists in delivering personalized learning experiences to address the unique needs of each learner. An important subfield of adaptive learning is learning path personalization: it aims at
Externí odkaz:
http://arxiv.org/abs/2305.06398
We introduce a new dataset named WikiVitals which contains a large graph of 48k mutually referred Wikipedia articles classified into 32 categories and connected by 2.3M edges. Our aim is to rigorously evaluate the contributions of three distinct sour
Externí odkaz:
http://arxiv.org/abs/2304.01235
Autor:
Lemberger, Pirmin, Oblin, Denis
Statisticians have warned us since the early days of their discipline that experimental correlation between two observations by no means implies the existence of a causal relation. The question about what clues exist in observational data that could
Externí odkaz:
http://arxiv.org/abs/2007.03940
Autor:
Lemberger, Pirmin
Text summarization is an NLP task which aims to convert a textual document into a shorter one while keeping as much meaning as possible. This pedagogical article reviews a number of recent Deep Learning architectures that have helped to advance resea
Externí odkaz:
http://arxiv.org/abs/2005.11988
Autor:
Lemberger, Pirmin, Panico, Ivan
Standard supervised machine learning assumes that the distribution of the source samples used to train an algorithm is the same as the one of the target samples on which it is supposed to make predictions. However, as any data scientist will confirm,
Externí odkaz:
http://arxiv.org/abs/2001.09994
Autor:
Lemberger, Pirmin
Why do large neural network generalize so well on complex tasks such as image classification or speech recognition? What exactly is the role regularization for them? These are arguably among the most important open questions in machine learning today
Externí odkaz:
http://arxiv.org/abs/1704.01312
Autor:
Lemberger, Pirmin.
Thèse no 1019 sciences EPF Lausanne.
Externí odkaz:
http://library.epfl.ch/theses/?nr=1019
Graph Markov Neural Networks (GMNN) have recently been proposed to improve regular graph neural networks (GNN) by including label dependencies into the semi-supervised node classification task. GMNNs do this in a theoretically principled way and use
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ec2cbdc7df03e1c3c75a5469974eca14