2 papers
cs.CV2026
Few-class Fidelity: Evaluating Explanations of Real-conditions CNN classifiers with Optimized Perturbations
Wistan Marchadour, Pedro Soto Vega, Franck Vermet +1
The wide use of Convolutional Neural Networks (CNN) in numerous domains and real-world classification applications is justified by their high precision and automation speed, helpin…
math.PR2026
On associative neural networks for sparse patterns with huge capacities
Matthias Löwe, Franck Vermet
Generalized Hopfield models with higher-order or exponential interaction terms are known to have substantially larger storage capacities than the classical quadratic model. On the…