no code implementations • ICLR 2018 • Chun-Min Chang, Chia-Ching Lin, Hung-Yi Ou Yang, Chin-Laung Lei, Kuan-Ta Chen
Besides, TESLA is applied to the VGG-16 model, which achieves 80\% accuracy using only 20\% of dot product terms on CIFAR-10 and also keeps 60\% accuracy using only 30\% of dot product terms on CIFAR-100, but the original IDP performs like a random guess in these two datasets at such low computation costs.