On May 14, the AI Facebook Research Team has published an article regarding Expire-Span, a human-brain like algorithm which learns to forget the irrelevant information. Expire-Span, a method that learns to retain the most important information and expire the irrelevant information. In practice, Expire-Span is a deep learning algorithm, which first predicts the most relevant information for a given task, and then it equips every information with an expiration date, namely a deadline. When the date expires, the associated information is forgotten. This aspect permits the Expire-Span algorithm to be very scalable in terms of memory.

Unlike human memory, most neural networks typically process information indiscriminately. On a small scale, this is functional. But current AI mechanisms used to selectively focus on certain parts of their input struggle with ever-larger quantities of information, incurring unsustainable computational costs. For this reason, Facebook researchers want to help future AIs to pay more attention to important data by assigning an expiration date. They announced the development of a novel method in deep learning, called Expire-Span, a first-of-its-kind operation that equips neural networks with the ability to forget at scale.