Dirichlet分布
人工神经网络
人工智能
航程(航空)
计算机科学
机器学习
班级(哲学)
主观逻辑
功能(生物学)
先验概率
贝叶斯概率
集合(抽象数据类型)
网(多面体)
数学
概率逻辑
工程类
进化生物学
生物
数学分析
航空航天工程
边值问题
程序设计语言
几何学
作者
Murat Şensoy,Lance Kaplan,Melih Kandemir
出处
期刊:Cornell University - arXiv
日期:2018-01-01
被引量:335
标识
DOI:10.48550/arxiv.1806.01768
摘要
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.
科研通智能强力驱动
Strongly Powered by AbleSci AI