Jay van Zyl @ ecosystem.Ai

Jay van Zyl @ ecosystem.Ai

Robust Adversarial Examples

We’ve created images that reliably fool neural network classifiers when viewed from varied scales and perspectives. This challenges a claim from last week that self-driving cars would be hard to trick maliciously since they capture images from multiple scales, angles, perspectives, and the like.


*This innocuous kitten photo, printed on

Imagine this: Creating new visual concepts by recombining familiar ones

Around two and a half thousand years ago a Mesopotamian trader gathered some clay, wood and reeds and changed humanity forever. Over time, their abacus would allow traders to keep track of goods and reconcile their finances, allowing economics to flour…

DeepMind expands to Canada with new research office in Edmonton, Alberta

DeepMind has always been a unique hybrid of startup culture and academia, and weve been lucky to collaborate with many of the best researchers from around the world. Today were thrilled to announce our next phase: the opening of DeepMinds first ever in…