资源分类
》 资源 》论文》Unimodal Probability Distributions for Deep Ordinal Classification

Unimodal Probability Distributions for Deep Ordinal Classification

2020-03-09 | |  55 |   39 |   0

Abstract

Probability distributions produced by the crossentropy loss for ordinal classification problems can possess undesired properties. We propose a straightforward technique to constrain discrete ordinal probability distributions to be unimodal via the use of the Poisson and binomial probability distributions. We evaluate this approach in the context of deep learning on two large ordinal image datasets, obtaining promising results.

上一篇：A Unified Maximum Likelihood Approach for Estimating Symmetric Properties of Discrete Distributions

下一篇：Robust Probabilistic Modeling with Bayesian Data Reweighting

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...