OpenAI and Uber create Virtual Petri Dish to find the best AI model for a task

Researchers affiliated with Uber AI and OpenAI proposed a new approach to neural architecture search (NAS), a technique that involves evaluating hundreds or thousands of AI models to identify the top performers. In a preprint paper, they claim their technique, called Synthetic Petri Dish, accelerates the most computationally intensive NAS steps while predicting model performance with higher accuracy than previous methods.

Link: OpenAI and Uber create Virtual Petri Dish to find the best AI model for a task
via venturebeat.com