Author: Messoudi, Soundouss; Rousseau, Sylvain; Destercke, Sébastien
Title: Deep Conformal Prediction for Robust Models Cord-id: qw9l3a6t Document date: 2020_5_18
ID: qw9l3a6t
Snippet: 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 pred
Document: 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.
Search related documents:
Co phrase search for related documents- adaptive method and machine learning: 1, 2, 3, 4, 5, 6
- long predict and machine learning: 1, 2, 3, 4, 5, 6, 7
- low probability and machine learning: 1, 2
Co phrase search for related documents, hyperlinks ordered by date