Abstract
The wide adoption of Convolutional Neural Networks (cnns) in applications where decision-making under uncertainty is fundamental, has brought a great deal of attention to the ability of these models to accurately quantify the uncertainty in their predictions. Previous work on combining cnns with Gaussian processes (gps) has been developed under the assumption that the predictive probabilities of these models are well-calibrated. In this paper we show that, in fact, current combinations of cnns and gps are miscalibrated. We propose a novel combination that considerably outperforms previous approaches on this aspect, while achieving state-of-the-art performance on image classification tasks.
Original language | English (US) |
---|---|
State | Published - 2020 |
Event | 22nd International Conference on Artificial Intelligence and Statistics, AISTATS 2019 - Naha, Japan Duration: Apr 16 2019 → Apr 18 2019 |
Conference
Conference | 22nd International Conference on Artificial Intelligence and Statistics, AISTATS 2019 |
---|---|
Country/Territory | Japan |
City | Naha |
Period | 04/16/19 → 04/18/19 |
ASJC Scopus subject areas
- Artificial Intelligence
- Statistics and Probability