6 papers
ReliableNet: A Chance-Constrained Approach to Trustworthy Classification in Deep Learning
Ange-Clément Akazan, Ineza Remy Mugenga, Abebe Geletu +2
A prediction that is both confident and wrong is a critical reliability failure because it can bypass abstention and human review precisely when the model is mistaken. Empirical ri…
Vision Tiny Recursion Model (ViTRM): Parameter-Efficient Image Classification via Recursive State Refinement
Ange-Clément Akazan, Abdoulaye Koroko, Verlon Roel Mbingui +3
The success of deep learning in computer vision has been driven by models of increasing scale, from deep Convolutional Neural Networks (CNN) to large Vision Transformers (ViT). Whi…
Splines-Based Feature Importance in Kolmogorov-Arnold Networks: A Framework for Supervised Tabular Data Dimensionality Reduction
Ange-Clément Akazan, Verlon Roel Mbingui
Feature selection is a key step in many tabular prediction problems, where multiple candidate variables may be redundant, noisy, or weakly informative. We investigate feature selec…
RRaPINNs: Residual Risk-Aware Physics Informed Neural Networks
Ange-Clément Akazan, Issa Karambal, Jean Medard Ngnotchouye +1
Physics-informed neural networks (PINNs) typically minimize average residuals, which can conceal large, localized errors. We propose Residual Risk-Aware Physics-Informed Neural Net…
Localized Weather Prediction Using Kolmogorov-Arnold Network-Based Models and Deep RNNs
Ange-Clement Akazan, Verlon Roel Mbingui, Gnankan Landry Regis N'guessan +1
Weather forecasting is crucial for managing risks and economic planning, particularly in tropical Africa, where extreme events severely impact livelihoods. Yet, existing forecastin…
Generating Tabular Data Using Heterogeneous Sequential Feature Forest Flow Matching
Ange-Clément Akazan, Alexia Jolicoeur-Martineau, Ioannis Mitliagkas
Privacy and regulatory constraints make data generation vital to advancing machine learning without relying on real-world datasets. A leading approach for tabular data generation i…