Here we present DeepLIFT (Deep Learning Important FeaTures), a method for decomposing the output prediction of a neural network on a specific input by backpropagating the contributions of all neurons in the network to every feature of the input.
The pre-dominant approach to language modeling to date is based on recurrent neural networks.
#11 best model for Language Modelling on One Billion Word
While humans easily recognize relations between data from different domains without any supervision, learning to automatically discover them is in general very challenging and needs many ground-truth pairs that illustrate the relations.
#9 best model for Facial Expression Translation on CelebA
We expand on previous work for image quality assessment to provide two new analyses for assessing the discriminability and diversity of samples from class-conditional image synthesis models.
#7 best model for Conditional Image Generation on CIFAR-10
We propose a novel technology to compensate this delay, so as to make the optimization behavior of ASGD closer to that of sequential SGD.
We obtain both state-of-the-art results and anecdotal evidence demonstrating the importance of the value distribution in approximate reinforcement learning.
SOTA for Atari Games on Atari 2600 Enduro