Deep Conformal Prediction for Robust Models - Archive ouverte HAL Access content directly
Conference Papers Year : 2020

Deep Conformal Prediction for Robust Models

Abstract

Deep networks, like some other learning models, can associate high trust to unreliable predictions. Making these models robust and reliable is therefore essential, especially for critical decisions. This experimental paper shows that the conformal prediction approach brings a convincing solution to this challenge. Conformal prediction consists in predicting a set of classes covering the real class with a user-defined frequency. In the case of atypical examples, the conformal prediction will predict the empty set. Experiments show the good behavior of the conformal approach, especially when the data is noisy.
Fichier principal
Vignette du fichier
IPMU_Paper_conformal.pdf (6.09 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02944875 , version 1 (21-09-2020)

Identifiers

Cite

Soundouss Messoudi, Sylvain Rousseau, Sébastien Destercke. Deep Conformal Prediction for Robust Models. 18th International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems (IPMU 2020), Aug 2020, Lisboa, Portugal. pp.528-540, ⟨10.1007/978-3-030-50146-4_39⟩. ⟨hal-02944875⟩
86 View
134 Download

Altmetric

Share

Gmail Facebook X LinkedIn More