Back to Search

Evidential deep learning to quantify classification uncertainty

Title	Evidential deep learning to quantify classification uncertainty
Author	Şensoy, Murat, Kaplan, L., Kandemir, M.
Publication Date:	2018
Publication Place	- Neural Information Processing Systems Foundation
Type	Document
Language	English
Digital	Yes
Manuscript	No
Library:	Özyeğin University
Library Asset ID	1049-5258
Record ID	3ca431f4-f9b7-42bd-8219-df874f6b6448
Library Location	Computer Science
Date	2018
Notes	United States Department of Defense US Army Research Laboratory (ARL) ; U.K. Ministry of Defence
Sample Text	Deterministic neural nets have been shown to learn effective predictors on a wide range of machine learning problems. However, as the standard approach is to train the network to minimize a prediction loss, the resultant model remains ignorant to its prediction confidence. Orthogonally to Bayesian neural nets that indirectly infer prediction uncertainty through weight uncertainties, we propose explicit modeling of the same using the theory of subjective logic. By placing a Dirichlet distribution on the class probabilities, we treat predictions of a neural net as subjective opinions and learn the function that collects the evidence leading to these opinions by a deterministic neural net from data. The resultant predictor for a multi-class classification problem is another Dirichlet distribution whose parameters are set by the continuous output of a neural net. We provide a preliminary analysis on how the peculiarities of our new loss function drive improved uncertainty estimation. We observe that our method achieves unprecedented success on detection of out-of-distribution queries and endurance against adversarial perturbations.
Cilt	31

View in source Özyeğin University Özyeğin University - Historical works, archives, and periodicals search engine

Özyeğin University

Evidential deep learning to quantify classification uncertainty

Author Şensoy, Murat, Kaplan, L., Kandemir, M.

Publication Date 2018

Publication Place - Neural Information Processing Systems Foundation

Type Document

Language English

Digital Yes

Manuscript No

Library Özyeğin University

Library Asset ID 1049-5258

Record ID 3ca431f4-f9b7-42bd-8219-df874f6b6448

Library Location Computer Science

Date 2018

Notes United States Department of Defense US Army Research Laboratory (ARL) ; U.K. Ministry of Defence

Sample Text Deterministic neural nets have been shown to learn effective predictors on a wide range of machine learning problems. However, as the standard approach is to train the network to minimize a prediction loss, the resultant model remains ignorant to its prediction confidence. Orthogonally to Bayesian neural nets that indirectly infer prediction uncertainty through weight uncertainties, we propose explicit modeling of the same using the theory of subjective logic. By placing a Dirichlet distribution on the class probabilities, we treat predictions of a neural net as subjective opinions and learn the function that collects the evidence leading to these opinions by a deterministic neural net from data. The resultant predictor for a multi-class classification problem is another Dirichlet distribution whose parameters are set by the continuous output of a neural net. We provide a preliminary analysis on how the peculiarities of our new loss function drive improved uncertainty estimation. We observe that our method achieves unprecedented success on detection of out-of-distribution queries and endurance against adversarial perturbations.

Cilt 31