One article from this weeks Nature outlook articles about cognitive science. You can even play the cognitive game :). The full set of articles is quite interesting!
Most self-respecting artists wouldn't agree to paint a portrait of a toilet in the middle of a field. Fortunately, advancements in artificial intelligence have given computers the ability to imagine just about any scenario, no matter how bizarre, and illustrate it. Take a look at this image.
Well, biased to the data it was trained on. Computing a net is pretty deterministic.
But not everything is perfectly correlated yet.
Still nice progress.
Genetic algorithms are a competitive alternative for training deep neural networks for reinforcement learning.
For paper see: https://arxiv.org/pdf/1712.06567.pdf
Not necessarily, I think it can be made to be much faster hybridizing it with backprop and Taylor maps. Its one ideas in the closet we still have not explored (Differential Intelligence: accelerating neuroevolution).
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.
"What if running the 26.2 miles of a marathon only felt like running 24.9 miles, or if you could improve your average running pace from 9:14 minutes/mile to 8:49 minutes/mile without weeks of training?"