Jérémie Sublime
YOU?
Author Swipe
Improving Fast Density Peak Clustering Using Mass Distance: m-FDPC Open
In this work, we introduce m-FDPC, a mass-based variant of the Fast Density Peak Clustering (FDPC) algorithm, aimed at improving both performance and ease of use in unsupervised learning tasks. Traditional FDPC relies on Euclidean distance…
The AI Race: Why Current Neural Network-based Architectures are a Poor Basis for Artificial General Intelligence Open
Artificial General Intelligence is the idea that someday an hypothetical agent will arise from artificial intelligence (AI) progresses, and will surpass by far the brightest and most gifted human minds. This idea has been around since the …
Can We Trust AI With Our Ears? A Cross-Domain Comparative Analysis of Explainability in Audio Intelligence Open
The rapid growth of deep learning has led to major successes in audio classification, but the “opaque” nature of these models slows down their use in important areas such as healthcare where trust is critical. This paper addresses this pro…
The Return of Pseudosciences in Artificial Intelligence: Have Machine Learning and Deep Learning Forgotten Lessons from Statistics and History? Open
In today's world, AI programs powered by Machine Learning are ubiquitous, and have achieved seemingly exceptional performance across a broad range of tasks, from medical diagnosis and credit rating in banking, to theft detection via video …
Application of explainable AI to healthcare: a review ⋆ Open
International audience
View article: Three-Dimensional Microarchitecture of Lamina Cribrosa Pores in High and Normal Tension Glaucoma Using Optical Coherence Tomography
Three-Dimensional Microarchitecture of Lamina Cribrosa Pores in High and Normal Tension Glaucoma Using Optical Coherence Tomography Open
Précis: The lamina cribrosa (LC) pores of patients with high-tension glaucoma (HTG) appear to take a more tortuous pathway than the LC pores of patients with non-glaucomatous (NG). Objective: To compare the LC pore microarchitecture in pat…
OBJECT DETECTION MODELS SENSITIVITY & ROBUSTNESS TO SATELLITE-BASED ADVERSARIAL ATTACKS Open
International audience
Artificial intelligence for dynamic and intelligent methane inventory  Open
Atmospheric methane contributes to approximately 20-30% of the current global radiative forcing by greenhouse gases. Despite the potential for a 39% reduction in emissions from the oil and gas sector at no net cost, the lack of dependable …
The AI Race: Why Current Neural Network-based Architectures are a Poor Basis for Artificial General Intelligence Open
Artificial General Intelligence is the idea that someday an hypothetical agent will arise from artificial intelligence (AI) progresses, and will surpass by far the brightest and most gifted human minds. This idea has been around since the …
Artificial Intelligence for Methane Mitigation : Through an Automated Determination of Oil and Gas Methane Emissions Profiles Open
International audience
O&GProfile : An automated method for attribution of satellite methane emissions detections to oil and gas sites and operators Open
International audience
Rethinking Collaborative Clustering: A Practical and Theoretical Study Within the Realm of Multi-view Clustering Open
With distributed and multi-view data being more and more ubiquitous, the last 20 years have seen a surge in the development of new multi-view methods. In unsupervised learning, these are usually classified under the paradigm of multi-view …
3D Orthogonal SD-OCT Volumes Registration for the Enhancement of Pores in Lamina Cribrosa Open
International audience
O&GProfile : Automated attribution of GHGSat point source methane emissions detections to O&G infrastructures for site emissions profile analysis (Permian) Open
Methane emissions are the second leading cause of global warming. Because of the near-term warming potential of atmospheric methane, reducing its emissions will be essential to achieve the UNFCCC climate objectives. Reducing methane emissi…
An Ensemble and Multi-View Clustering Method Based on Kolmogorov Complexity Open
The ability to build more robust clustering from many clustering models with different solutions is relevant in scenarios with privacy-preserving constraints, where data features have a different nature or where these features are not avai…
Context-aware Attention U-Net for the segmentation of pores in Lamina Cribrosa using partial points annotation Open
Glaucoma is the second leading cause of blindness in the world. Although its physiopathology remains unclear, the lamina cribrosa, a 3D mesh-like structure consisting of pores, that allow the axons passing through to join the brain, has be…
View article: Low Complexity LSTM-NN-Based Receiver for Vehicular Communications in the Presence of High-Power Amplifier Distortions
Low Complexity LSTM-NN-Based Receiver for Vehicular Communications in the Presence of High-Power Amplifier Distortions Open
Vehicular communications are an important focus of studies for 5G applications and beyond. However, in a scenario with doubly-selective and highly variable channel characteristics, tracking the wireless channel to ensure communication reli…
Unsupervised Approaches for the Segmentation of Dry ARMD Lesions in Eye Fundus cSLO Images Open
Age-related macular degeneration (ARMD), a major cause of sight impairment for elderly people, is still not well understood despite intensive research. Measuring the size of the lesions in the fundus is the main biomarker of the severity o…
The 2011 Tohoku Tsunami from the Sky: A Review on the Evolution of Artificial Intelligence Methods for Damage Assessment Open
The Tohoku tsunami was a devastating event that struck North-East Japan in 2011 and remained in the memory of people worldwide. The amount of devastation was so great that it took years to achieve a proper assessment of the economical and …
Contributions to modern unsupervised learning: Case studies of multi-view clustering and unsupervised Deep Learning Open
This document is the manuscript presented in order to obtain the Habilitation a Diriger des Recherches of Sorbonne University (France), prepared at ISEP Engineering School where I am currently an Associate Professor. My main professional a…
Deep Cooperative Reconstruction with Security Constraints in multi-view environments Open
International audience
Unsupervised Change Detection using Joint Autoencoders for Age-Related Macular Degeneration Progression Open
International audience
Analyzing Age-Related Macular Degeneration Progression in Patients with Geographic Atrophy Using Joint Autoencoders for Unsupervised Change Detection Open
Age-Related Macular Degeneration (ARMD) is a progressive eye disease that slowly causes patients to go blind. For several years now, it has been an important research field to try to understand how the disease progresses and find effective…