Blogue
Classificateur flou optimisé par dégradé: Une étude de référence contre Modèles à la pointe de la technologie
This paper presents a performance benchmarking study of a Gradient-Optimized Fuzzy Inference System (Petite amie) classifier against several state-of-the-art machine learning models, y compris la forêt aléatoire, XGBoost, Régression logistique, Machines à vecteurs de support, et réseaux de neurones. The evaluation was conducted across five datasets from the...
Codage de termes pour la combinatoire extrême: Dispersion et complexité Dichotomies
We introduce \emph{Codage des termes}, a novel framework for analysing extremal problems in discrete mathematics by encoding them as finite systems of \emph{équations de termes} (et, en option, \emph{contraintes de non-égalité}). In its basic form, toutes les variables s'étendent sur un seul domaine, and we seek an...
Améliorer les performances du classificateur avec des données basées sur l'opposition Transformation
Dans ce document, we introduce a novel data transformation framework based on Opposition-Based Learning (OBL) to boost the performance of traditional classification algorithms. Originally developed to accelerate convergence in optimization tasks, OBL is leveraged here to generate synthetic opposite samples that replace...
Une approche géométrique des problèmes d'optimisation et de science des données
We give new results for problems in computational and statistical machine learning using tools from high-dimensional geometry and probability. Nous divisons notre traitement en deux parties. Dans la première partie, we focus on computational considerations in optimization. Spécifiquement, we give new algorithms...
Alignement des formes via convection non linéaire Allen-Cahn
This paper demonstrates the impact of a phase field method on shape registration to align shapes of possibly different topology. It yields new insights into the building of discrepancy measures between shapes regardless of topology, which would have applications in fields of...
Les modèles d'affect ont une faible généralisabilité au discours atypique
Les conditions de parole et de voix peuvent altérer les propriétés acoustiques de la parole, which could impact the performance of paralinguistic models for affect for people with atypical speech. We evaluate publicly available models for recognizing categorical and dimensional affect from speech on a dataset...
Correspondance Regex de sous-séquence de temps linéaire et de super-séquence
It is well-known that checking whether a given string $w$ matches a given regular expression $r$ can be done in quadratic time $O(|w|\cdot |r|)$ and that this cannot be improved to a truly subquadratic running time of $O((|w|\cdot |r|)^{1-\épsilon})$ assuming the strong...
Profond, data-driven modeling of room acoustics: literature review and research perspectives
Our everyday auditory experience is shaped by the acoustics of the indoor environments in which we live. Room acoustics modeling is aimed at establishing mathematical representations of acoustic wave propagation in such environments. These representations are relevant to a variety of problems...
GENCNIPPET: Automated Generation of Code Snippets for Supporting Programming Questions
Context: Software developers often ask questions on Technical Q&A forums like Stack Overflow (SO) to seek solutions to their programming-related problems (par ex., errors and unexpected behavior of code). Problem: Many questions miss required code snippets due to the lack of readily available...
CHIME All-sky Multiday Pulsar Stacking Search (CHAMPSS): System Overview and First Discoveries
We describe the CHIME All-sky Multiday Pulsar Stacking Search (CHAMPSS) project. This novel radio pulsar survey revisits the full Northern Sky daily, offering unprecedented opportunity to detect highly intermittent pulsars, as well as faint sources via long-term data stacking. CHAMPSS uses the...