no code implementations • 26 May 2024 • Menghao Waiyan William Zhu, Ercan Engin Kuruoğlu
We find that for small datasets, quadratic approximation of the previous loss function leads to poor results, even with full Hessian computation, and NC could significantly improve the predictive performance, while for large datasets, when used with a fixed pre-trained feature extractor, AQC provides superior predictive performance.
no code implementations • 17 Nov 2023 • Xueqiong Yuan, Jipeng Li, Ercan Engin Kuruoğlu
A common approach for obtaining robustness to noise has been to train deep learning systems with data augmented with Gaussian noise.