Loading...
3IA Côte d'Azur - Interdisciplinary Institute for Artificial Intelligence
3IA Côte d'Azur est l'un des quatre "Instituts interdisciplinaires d'intelligence artificielle" créés en France en 2019. Son ambition est de créer un écosystème innovant et influent au niveau local, national et international. L'institut 3IA Côte d'Azur est piloté par Université Côte d'Azur en partenariat avec les grands partenaires de l'enseignement supérieur et de la recherche de la région niçoise et de Sophia Antipolis : CNRS, Inria, INSERM, EURECOM, SKEMA Business School. L'institut 3IA Côte d'Azur est également soutenu par l'ECA, le CHU de Nice, le CSTB, le CNES, l'Institut Data ScienceTech et l'INRAE. Le projet a également obtenu le soutien de plus de 62 entreprises et start-ups.
Derniers dépôts
-
Riccardo Taiello, Cansiz Sergen, Vesin Marc, Cremonesi Francesco, Innocenti Lucia, et al.. Enhancing Privacy in Federated Learning: Secure Aggregation for Real-World Healthcare Applications. 5-th MICCAI Workshop on Distributed, Collaborative and Federated Learning in Conjunction with MICCAI 2024, Oct 2024, Marrachech, Morocco. ⟨hal-04855481⟩
-
Riccardo Taiello, Melek Önen, Clémentine Gritti, Marco Lorenzi. Let Them Drop: Scalable and Efficient Federated Learning Solutions Agnostic to Stragglers. The 19th International Conference on Availability, Reliability and Security (ARES 2024), Jul 2024, Wien, Austria. ⟨10.1145/3664476.3664488⟩. ⟨hal-04650828⟩
-
Louis Ohl, Pierre-Alexandre Mattei, Charles Bouveyron, Mickaël Leclercq, Arnaud Droit, et al.. Sparse and geometry-aware generalisation of the mutual information for joint discriminative clustering and feature selection. Statistics and Computing, 2024, 34 (5), pp.155. ⟨10.1007/s11222-024-10467-9⟩. ⟨hal-04755942⟩
-
Alessandro Viani, Boris A Gutman, Emile d'Angremont, Marco Lorenzi. Disease Progression Modelling and Stratification for detecting sub-trajectories in the natural history of pathologies: application to Parkinson's Disease trajectory modelling. Longitudinal Disease Tracking and Modelling with Medical Images and Data, Oct 2024, Marrachech, Morocco. ⟨hal-04833565⟩
Documents en texte intégral
737
Notices
332
Statistiques par discipline
Mots clés
Electrophysiology
Super-resolution
Apprentissage profond
Image fusion
Medical imaging
Ontology Learning
Information Extraction
Semantic web
Convolutional Neural Networks
Uncertainty
Machine learning
Argument mining
Arguments
Deep learning
Alzheimer's disease
Extracellular matrix
Diffusion strategy
Macroscopic traffic flow models
SHACL
Geometric graphs
CNN
Sparsity
Computer vision
Clinical trials
Distributed optimization
FPGA
Hyperspectral data
Co-clustering
Convolutional neural network
Diffusion MRI
Unsupervised learning
Graph neural networks
Spiking Neural Networks
FDG PET
Federated learning
Semantic Web
Privacy
Linked data
Convergence analysis
Anomaly detection
Linked Data
Knowledge graphs
Change point detection
Echocardiography
Neural networks
Grammatical Evolution
Autoencoder
Argument Mining
Dense labeling
Isomanifolds
Artificial Intelligence
Chernoff information
Optimization
Topological Data Analysis
Federated Learning
Latent block model
Consensus
Adversarial classification
Contrastive learning
Segmentation
NLP Natural Language Processing
Brain-inspired computing
Hyperbolic systems of conservation laws
Image segmentation
Healthcare
Domain adaptation
Clustering
NLP
Visualization
OPAL-Meso
Knowledge graph
Atrial Fibrillation
Semantic segmentation
MRI
SPARQL
Coxeter triangulation
Graph signal processing
Excursion sets
Extreme value theory
Explainable AI
Artificial intelligence
Electrocardiogram
Persistent homology
Autonomous vehicles
Caching
Computational Topology
53B20
Computing methodologies
Fluorescence microscopy
Convolutional neural networks
Biomarkers
Multi-Agent Systems
Cable-driven parallel robot
COVID-19
Deep Learning
Web of Things
RDF
Spiking neural networks
Predictive model
Atrial fibrillation