Just out - I wish I could understand this :(

Paper: https://arxiv.org/abs/1806.02404

Dataset automatically constructed from public images uploaded by users on FB/Instagram with hashtags used as labels! They refer to this as 'weakly supervised learning'. Then neural net fine-tuned for ImageNet and achieved record 85.4% accuracy.

Took 2000 GPUs over 2 weeks to train :)

This has attracted a lot of attention in the DL community lately. Article: https://lilianweng.github.io/lil-log/2017/09/28/anatomize-deep-learning-with-information-theory.html Paper: https://arxiv.org/pdf/1703.00810.pdf

Genetic algorithms are a competitive alternative for training deep neural networks for reinforcement learning. For paper see: https://arxiv.org/pdf/1712.06567.pdf