A5050516915- Rough Sets and Fuzzy Logic
- Data Mining Algorithms and Applications
- Data Management and Algorithms
- Logic, Reasoning, and Knowledge
- Advanced Clustering Algorithms Research
- Semantic Web and Ontologies
- Constraint Satisfaction and Optimization
- Bayesian Modeling and Causal Inference
- Natural Language Processing Techniques
- Text and Document Classification Technologies
- Time Series Analysis and Forecasting
- Image Retrieval and Classification Techniques
- Advanced Database Systems and Queries
- Neural Networks and Applications
- Imbalanced Data Classification Techniques
- Advanced Algebra and Logic
- Machine Learning and Algorithms
- Data Quality and Management
- Fuzzy Logic and Control Systems
- Domain Adaptation and Few-Shot Learning
- Complex Systems and Time Series Analysis
- AI-based Problem Solving and Planning
- Face and Expression Recognition
- Advanced Image and Video Retrieval Techniques
- Logic, programming, and type systems
Institut National des Sciences Appliquées Centre Val de Loire
2015-2025
Laboratoire d'Informatique Fondamentale d'Orléans
2015-2024
Centre Val de Loire
2015-2024
Université d'Orléans
2011-2023
Laboratoire d’Informatique Fondamentale de Marseille
2003-2020
Université Paris Cité
1986-2005
Université Paris-Sud
1990-2005
University of North Carolina at Charlotte
1997
Conference Board
1997
Saarland University
1997
It is well known that modeling with constraints networks require a fair expertise. Thus tools able to automatically generate such have gained major interest. The contribution of this paper set new framework based on Inductive Logic Programming build constraint model from solutions and non-solutions related problems. expressed in middle-level language. On particular relational learning problem, traditional top-down search methods fall into blind bottom-up produce too expensive coverage tests....
This paper proposes a tentative and original survey of meeting points between Knowledge Representation Reasoning (KRR) Machine Learning (ML), two areas which have been developed quite separately in the last four decades. First, some common concerns are identified discussed such as types representation used, roles knowledge data, lack or excess information, need for explanations causal understanding. Then, is organised seven sections covering most territory where KRR ML meet. We start with...
The advent of high-resolution instruments for time-series sampling poses added complexity the formal definition thematic classes in remote sensing domain-required by supervised methods-while unsupervised methods ignore expert knowledge and intuition. Constrained clustering is becoming an increasingly popular approach data mining because it offers a solution to these problems; however, its application relatively unknown. This article addresses this divide adapting publicly available...
Gene regulatory network inference remains a challenging problem in systems biology despite the numerous approaches that have been proposed. When substantial knowledge on gene is already available, supervised appropriate. Such method builds binary classifier able to assign class (Regulation/No regulation) an ordered pair of genes. Once learnt, pairwise can be used predict new regulations. In this work, we explore framework Markov Logic Networks (MLN) combine features probabilistic graphical...
This paper introduces a deep learning method for image classification that leverages knowledge formalised as graph created from information represented by pairs attribute/value. The proposed investigates loss function adaptively combines the classical cross-entropy commonly used in with novel penalty function. is derived representation of nodes after embedding and incorporates proximity between class nodes. Its formulation enables model to focus on identifying boundary most challenging...
In many settings just finding a good clustering is insufficient and an explanation of the required. If features used to perform are interpretable then methods such as conceptual can be used. However, in applications this not case particularly for image, graph other complex data. Here we explore setting where set discrete tags each instance available. We formulate descriptive problem bi-objective optimization simultaneously find compact clusters using describe them tags. present our...