1. Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter;sanh;ArXiv Preprint,2019
2. Fast Exact Multiplication by the Hessian
3. Very deep convolutional networks for large-scale image recognition;simonyan;ArXiv Preprint,2014
4. Deep residual learning for image recognition;he;CoRR,2015
5. Learning word vectors for sentiment analysis;maas;Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics Human Language Technologies,0