CreINNs: Credal-Set Interval Neural Networks for Uncertainty Estimation in Classification Tasks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929687167500288 |
|---|---|
| author | Wang, Kaizheng Shariatmadar, Keivan Manchingal, Shireen Kudukkil Cuzzolin, Fabio Moens, David Hallez, Hans |
| author_facet | Wang, Kaizheng Shariatmadar, Keivan Manchingal, Shireen Kudukkil Cuzzolin, Fabio Moens, David Hallez, Hans |
| contents | Effective uncertainty estimation is becoming increasingly attractive for enhancing the reliability of neural networks. This work presents a novel approach, termed Credal-Set Interval Neural Networks (CreINNs), for classification. CreINNs retain the fundamental structure of traditional Interval Neural Networks, capturing weight uncertainty through deterministic intervals. CreINNs are designed to predict an upper and a lower probability bound for each class, rather than a single probability value. The probability intervals can define a credal set, facilitating estimating different types of uncertainties associated with predictions. Experiments on standard multiclass and binary classification tasks demonstrate that the proposed CreINNs can achieve superior or comparable quality of uncertainty estimation compared to variational Bayesian Neural Networks (BNNs) and Deep Ensembles. Furthermore, CreINNs significantly reduce the computational complexity of variational BNNs during inference. Moreover, the effective uncertainty quantification of CreINNs is also verified when the input data are intervals. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_05043 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CreINNs: Credal-Set Interval Neural Networks for Uncertainty Estimation in Classification Tasks Wang, Kaizheng Shariatmadar, Keivan Manchingal, Shireen Kudukkil Cuzzolin, Fabio Moens, David Hallez, Hans Machine Learning Artificial Intelligence Effective uncertainty estimation is becoming increasingly attractive for enhancing the reliability of neural networks. This work presents a novel approach, termed Credal-Set Interval Neural Networks (CreINNs), for classification. CreINNs retain the fundamental structure of traditional Interval Neural Networks, capturing weight uncertainty through deterministic intervals. CreINNs are designed to predict an upper and a lower probability bound for each class, rather than a single probability value. The probability intervals can define a credal set, facilitating estimating different types of uncertainties associated with predictions. Experiments on standard multiclass and binary classification tasks demonstrate that the proposed CreINNs can achieve superior or comparable quality of uncertainty estimation compared to variational Bayesian Neural Networks (BNNs) and Deep Ensembles. Furthermore, CreINNs significantly reduce the computational complexity of variational BNNs during inference. Moreover, the effective uncertainty quantification of CreINNs is also verified when the input data are intervals. |
| title | CreINNs: Credal-Set Interval Neural Networks for Uncertainty Estimation in Classification Tasks |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2401.05043 |