1. What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?, 2017
: Infer epistemic uncertainty and aleatoric uncertainty using Bayesian neural networks.
What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? Part of: Advances in Neural Information Processing Systems 30 (NIPS 2017) [PDF] [BibTeX] [Supplemental] [Reviews] Authors Conference Event Type: Poster Abstract There are two majo
papers.nips.cc
2. Predictive Uncertainty Estimation via Prior Networks, 2018
: Epistemic uncertainty + aleatoric uncertainty + out of distribution estimation using adversarial data.
https://papers.nips.cc/paper/7936-predictive-uncertainty-estimation-via-prior-networks
Predictive Uncertainty Estimation via Prior Networks
Predictive Uncertainty Estimation via Prior Networks Part of: Advances in Neural Information Processing Systems 31 (NIPS 2018) [PDF] [BibTeX] [Supplemental] [Reviews] Authors Conference Event Type: Poster Abstract Estimating how uncertain an AI system is i
papers.nips.cc
3. Uncertainty-Aware Learning from Demonstration using Mixture Density Networks with Sampling-Free Variance Modeling, 2018
: Sampling free uncertainty estimation using mixture density networks.
https://arxiv.org/abs/1709.02249
Uncertainty-Aware Learning from Demonstration using Mixture Density Networks with Sampling-Free Variance Modeling
In this paper, we propose an uncertainty-aware learning from demonstration method by presenting a novel uncertainty estimation method utilizing a mixture density network appropriate for modeling complex and noisy human behaviors. The proposed uncertainty a
arxiv.org
4. To Trust Or Not To Trust A Classifier, 2018
: Propose thetrust score which measures theagreement between the classifier and a modified nearest-neighbor classifier onthe testing example.
http://papers.nips.cc/paper/7798-to-trust-or-not-to-trust-a-classifier
To Trust Or Not To Trust A Classifier
To Trust Or Not To Trust A Classifier Part of: Advances in Neural Information Processing Systems 31 (NIPS 2018) [PDF] [BibTeX] [Supplemental] [Reviews] Authors Conference Event Type: Poster Abstract Knowing when a classifier's prediction can be trusted is
papers.nips.cc
5. Evidential Deep Learning to Quantify ClassificationUncertainty, 2018
: Similart to 'Predictive Uncertainty Estimation via Prior Networks'
http://papers.nips.cc/paper/7580-evidential-deep-learning-to-quantify-classification-uncertainty
Evidential Deep Learning to Quantify Classification Uncertainty
Evidential Deep Learning to Quantify Classification Uncertainty Part of: Advances in Neural Information Processing Systems 31 (NIPS 2018) [PDF] [BibTeX] [Supplemental] [Reviews] Authors Conference Event Type: Poster Abstract Deterministic neural nets have
papers.nips.cc
6. Novel Uncertainty Framework for Deep Learning Ensembles, 2019
: Ensemble of classifiers
https://arxiv.org/abs/1904.04917
Novel Uncertainty Framework for Deep Learning Ensembles
Deep neural networks have become the default choice for many of the machine learning tasks such as classification and regression. Dropout, a method commonly used to improve the convergence of deep neural networks, generates an ensemble of thinned networks
arxiv.org
7. Generative Probabilistic Novelty Detection withAdversarial Autoencoders, 2018
: Novelty detection (using reconstruction loss)
Generative Probabilistic Novelty Detection with Adversarial Autoencoders
Generative Probabilistic Novelty Detection with Adversarial Autoencoders Part of: Advances in Neural Information Processing Systems 31 (NIPS 2018) [PDF] [BibTeX] [Supplemental] [Reviews] Authors Conference Event Type: Poster Abstract Novelty detection is t
papers.nips.cc
'Enginius > Machine Learning' 카테고리의 다른 글
| Gaussian Process를 이용한 mu, dmu, ddmu 구하기 (0) | 2021.02.01 |
|---|---|
| Point Process in a Ball (0) | 2020.02.21 |
| Curation of RL papers (0) | 2019.12.06 |
| VAE에 대한 잡설 (2) | 2018.08.03 |
| 2018년 기존 최신 논문들 (RL 위주) (1) | 2018.04.07 |
