AI & ML
Reptile: A scalable meta-learning algorithm
OpenAI Blog0 views
We’ve developed a simple meta-learning algorithm called Reptile which works by repeatedly sampling a task, performing stochastic gradient descent on it, and updating the initial parameters towards the final parameters learned on that task. Reptile is the application of the Shortest Descent algorithm to the meta-learning setting, and is mathematically similar to first-order MAML (which is a version of the well-known MAML algorithm) that only needs black-box access to an optimizer such as SGD or Adam, with similar computational efficiency and performance.
Source:https://openai.com/index/reptileRelated posts

The Future of AI Jobs May Be Outside the Tech Industry
0HackerNoon
Vulcan rocket fails during launch, dealing major blow to SpaceX competitors
0Ars Technica
Indian chip startup Bharat Semi lands $24M seed round as it eyes global AI sensor market
0TechCrunch
Chemical spills into drainage ditch at SpaceXAI in Southaven
0Hacker News New
Extinct 'vampire camel' once stalked North American plains – Science – AAAS
0Hacker News New
When Failure Becomes Expensive: How Systems Reorder What Is Worth Protecting
0Hacker News New