Estimating Uncertainty with Implicit Quantile Network
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909296985374720 |
|---|---|
| author | Lim, Yi Hung |
| author_facet | Lim, Yi Hung |
| contents | Uncertainty quantification is an important part of many performance critical applications. This paper provides a simple alternative to existing approaches such as ensemble learning and bayesian neural networks. By directly modeling the loss distribution with an Implicit Quantile Network, we get an estimate of how uncertain the model is of its predictions. For experiments with MNIST and CIFAR datasets, the mean of the estimated loss distribution is 2x higher for incorrect predictions. When data with high estimated uncertainty is removed from the test dataset, the accuracy of the model goes up as much as 10%. This method is simple to implement while offering important information to applications where the user has to know when the model could be wrong (e.g. deep learning for healthcare). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_14525 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Estimating Uncertainty with Implicit Quantile Network Lim, Yi Hung Machine Learning Artificial Intelligence Neural and Evolutionary Computing Uncertainty quantification is an important part of many performance critical applications. This paper provides a simple alternative to existing approaches such as ensemble learning and bayesian neural networks. By directly modeling the loss distribution with an Implicit Quantile Network, we get an estimate of how uncertain the model is of its predictions. For experiments with MNIST and CIFAR datasets, the mean of the estimated loss distribution is 2x higher for incorrect predictions. When data with high estimated uncertainty is removed from the test dataset, the accuracy of the model goes up as much as 10%. This method is simple to implement while offering important information to applications where the user has to know when the model could be wrong (e.g. deep learning for healthcare). |
| title | Estimating Uncertainty with Implicit Quantile Network |
| topic | Machine Learning Artificial Intelligence Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2408.14525 |