Parametric Variational Linear Units (PVLUs) in Deep Convolutional Networks

no code implementations • 23 Oct 2021 • Aarush Gupta, Shikhar Ahuja

The VGG-16 and VGG-19 models experience relative error reductions of 9. 5% and 10. 7% on CIFAR-10, respectively, after the substitution of ReLU with PVLU.

Data Augmentation Transfer Learning