Understandable Relu Neural Network For Signal Classification - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Understandable Relu Neural Network For Signal Classification

Résumé

ReLU neural networks suffer from a problem of explainability because they partition the input space into a lot of polyhedrons. This paper proposes a constrained neural network model that replaces polyhedrons by orthotopes: each hidden neuron processes only a single component of the input signal. When the number of hidden neurons is large, we show that our neural network is equivalent to a logistic regression whose input is a non-linear transformation of the processed signal. Hence, the training of our neural network always converges to a unique solution. Numerical simulations show that the loss of performance with respect to state-of-the-art methods is negligible even though our neural network is strongly constrained on robustness and explainability.
Fichier non déposé

Dates et versions

hal-04195962 , version 1 (05-09-2023)

Identifiants

Citer

Marie Guyomard, Susana Barbosa, Lionel Fillatre. Understandable Relu Neural Network For Signal Classification. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Jun 2023, Rhodos, Greece. ⟨10.1109/ICASSP49357.2023.10095422⟩. ⟨hal-04195962⟩
10 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More