All articles

News

Adversarial Examples Can Improve Image Recognition

Adversarial examples are instances with small, intentional feature perturbations that cause a machine learning model to make a false prediction. A number of methods for generating but also defending from…
News

OpenAI Releases Safety Gym for Reinforcement Learning

OpenAI has announced the release of SafetyGym – a set of environments and tools for testing reinforcement learning agents towards safety constraints during training. Considering the deployment and real-world applications…