Evidential deep learning to quantify classification uncertainty

Name: Evidential deep learning to quantify classification uncertainty
Author: Şensoy, Murat, Kaplan, L., Kandemir, M.

İsim	Evidential deep learning to quantify classification uncertainty
Yazar	Şensoy, Murat, Kaplan, L., Kandemir, M.
Basım Tarihi:	2018
Basım Yeri	- Neural Information Processing Systems Foundation
Tür	Belge
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	1049-5258
Kayıt Numarası	3ca431f4-f9b7-42bd-8219-df874f6b6448
Lokasyon	Computer Science
Tarih	2018
Notlar	United States Department of Defense US Army Research Laboratory (ARL) ; U.K. Ministry of Defence
Örnek Metin	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

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

Evidential deep learning to quantify classification uncertainty

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

Basım Tarihi 2018

Basım Yeri - Neural Information Processing Systems Foundation

Tür Belge

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 1049-5258

Kayıt Numarası 3ca431f4-f9b7-42bd-8219-df874f6b6448

Lokasyon Computer Science

Tarih 2018

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

Örnek Metin 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