258 citations · 1.1k across the 17 of their papers we have counts for
4 papers · 1 filter
The Reversible Residual Network: Backpropagation Without Storing Activations
Aidan N. Gomez, Mengye Ren, Raquel Urtasun +1
Deep residual networks (ResNets) have significantly pushed forward the state-of-the-art on image classification, increasing in performance as networks grow both deeper and wider. H…
One Model To Learn Them All
Lukasz Kaiser, Aidan N. Gomez, Noam Shazeer +4
Deep learning yields great results across many fields, from speech recognition, image classification, to translation. But for each problem, getting a deep model to work well involv…
Depthwise Separable Convolutions for Neural Machine Translation
Lukasz Kaiser, Aidan N. Gomez, Francois Chollet
Depthwise separable convolutions reduce the number of parameters and computation used in convolutional operations while increasing representational efficiency. They have been shown…
Attention Is All You Need
Ashish Vaswani, Noam Shazeer, Niki Parmar +5
The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also conne…