From the 2 of 5.3k papers with an AI index.
29.3k citations
- Centre National de la Recherche ScientifiqueFR1.2k papers
- Sorbonne UniversitéFR664 papers
- Université Paris-SaclayFR657 papers
- Université Paris CitéFR617 papers
- University of ZurichCH607 papers
- Istituto Nazionale di Fisica Nucleare, Sezione di BolognaIT606 papers
- Institut National de Physique Nucléaire et de Physique des ParticulesFR603 papers
- Istituto Nazionale di Fisica Nucleare, Sezione di Roma IIT596 papers
- Aix-Marseille UniversitéFR590 papers
- European Organization for Nuclear ResearchCH586 papers
- University of OxfordGB581 papers
- Istituto Nazionale di Fisica Nucleare, Sezione di GenovaIT579 papers
19 papers · 2 filters
Do Not Trust a Model Because It is Confident: Uncovering and Characterizing Unknown Unknowns to Student Success Predictors in Online-Based Learning
Roberta Galici, Tanja Käser, Gianni Fenu +1
Student success models might be prone to develop weak spots, i.e., examples hard to accurately classify due to insufficient representation during model creation. This weakness is o…
Fine-grained Population Mapping from Coarse Census Counts and Open Geodata
Nando Metzger, John E. Vargas-Muñoz, Rodrigo C. Daudt +6
Fine-grained population maps are needed in several domains, like urban planning, environmental monitoring, public health, and humanitarian operations. Unfortunately, in many countr…
On double-descent in uncertainty quantification in overparametrized models
Lucas Clarté, Bruno Loureiro, Florent Krzakala +1
Uncertainty quantification is a central challenge in reliable and trustworthy machine learning. Naive measures such as last-layer scores are well-known to yield overconfident estim…
Accelerating Transfer Learning with Near-Data Computation on Cloud Object Stores
Diana Petrescu, Arsany Guirguis, Do Le Quoc +3
Storage disaggregation underlies today's cloud and is naturally complemented by pushing down some computation to storage, thus mitigating the potential network bottleneck between t…
Machine Learning for Optical Motion Capture-driven Musculoskeletal Modelling from Inertial Motion Capture Data
Abhishek Dasgupta, Rahul Sharma, Challenger Mishra +1
Marker-based Optical Motion Capture (OMC) systems and associated musculoskeletal (MSK) modelling predictions offer non-invasively obtainable insights into in vivo joint and muscle…
Time-to-Green predictions for fully-actuated signal control systems with supervised learning
Alexander Genser, Michail A. Makridis, Kaidi Yang +3
Recently, efforts have been made to standardize signal phase and timing (SPaT) messages. These messages contain signal phase timings of all signalized intersection approaches. This…