The purported "black box"' nature of neural networks is a barrier to adoption in applications where interpretability is essential.
The prevalent approach to sequence to sequence learning maps an input sequence to a variable length output sequence via recurrent neural networks.
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.
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 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.
#5 best model for Conditional Image Generation on CIFAR-10
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 Asterix