Researchers at Uber and Google are working on modifications to the two most popular deep-learning frameworks that will enable them to handle probability. This will provide a way for the smartest AI programs to measure their confidence in a prediction or a decision—essentially, to know when they should doubt themselves.
The new approach could be useful in critical scenarios involving self-driving cars and other autonomous machines.
The work reflects the realization that uncertainty is a key aspect of human reasoning and intelligence. Adding it to AI programs could make them smarter and less prone to blunders.MORE