neural networks neural networks heats up. heats up.
What could a decade-old game possibly have to do with a state-of-the-art training? the-art neural networks? More than you'd think. See, by virtue of Technology Review, the techniques that some people are using to make the game's AI smarter and harder to beat can be carried over to neural network development.
See, in StarCraft II, you ' managing tasks and fighting with an opponent who is trying to wipe you out. It's a complicated task that humans are good at, but machines can struggle with. Sound kind of familiar?
What's happening with StarCraft II's AI is thatis using a type of algorithm called population-based training to mimic natural selection , The algorithm shortcuts the learning process by starting with the most efficient units and then basing future adaptations on those.
The same thing is happening with self-driving development.
"One of the key challenges for anyone doing machine learning in an industrial system is that it is most efficient and useful." Matthieu Devin, Director of Machine Learning Infrastructure at Waymo, said in an interview with MIT Technology Review. And when you retrain, you may need to tweak your parameters. "
Google has already commercialized some of its machine-learning technology, but it's specifically using this population-based training model on its fleet of Waymo self-driving vehicles, which has been widely used for the purposes ofand one that has driven billions and simulated miles. [1
A ride on public streets in Waymo One