Back to Search
Start Over
μDARTS: Model Uncertainty-Aware Differentiable Architecture Search
- Source :
- IEEE Access, Vol 10, Pp 98670-98682 (2022)
- Publication Year :
- 2022
- Publisher :
- IEEE, 2022.
-
Abstract
- We present a Model Uncertainty-aware Differentiable ARchiTecture Search ( $\mu $ DARTS) that optimizes neural networks to simultaneously achieve high accuracy and low uncertainty. We introduce concrete dropout within DARTS cells and include a Monte-Carlo regularizer within the training loss to optimize the concrete dropout probabilities. A predictive variance term is introduced in the validation loss to enable searching for architecture with minimal model uncertainty. The experiments on CIFAR10, CIFAR100, SVHN, and ImageNet verify the effectiveness of $\mu $ DARTS in improving accuracy and reducing uncertainty compared to existing DARTS methods. Moreover, the final architecture obtained from $\mu $ DARTS shows higher robustness to noise at the input image and model parameters compared to the architecture obtained from existing DARTS methods.
Details
- Language :
- English
- ISSN :
- 21693536
- Volume :
- 10
- Database :
- Directory of Open Access Journals
- Journal :
- IEEE Access
- Publication Type :
- Academic Journal
- Accession number :
- edsdoj.128a3760bd924915b9b18a56a1aed11c
- Document Type :
- article
- Full Text :
- https://doi.org/10.1109/ACCESS.2022.3206373