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.

Facebook AI Research (FAIR) open-sourced Expire-Span, a deep-learning technique that learns which items in an input sequence should be remembered, reducing the memory and computation requirements for AI. FAIR showed that Transformer models that incorporate Expire-Span can scale to sequences of tens of thousands of items with improved performance compared to previous models. The research team described the technique and several experiments in a paper to be presented at the upcoming International Conference on Machine Learning (ICML). Expire-Span allows sequential AI models to "forget" events that are no longer relevant. When incorporated into self-attention models, such as the Transformer, Expire-Span reduces the amount of memory needed, allowing the model to handle longer sequences, which is key to improved performance on many tasks, such as natural language processing (NLP).

Do you read me, HAL?" said astronaut Dave Bowman, desperately trying to keep his emotions in check. There was a pause and then, in an emotionless monotone, the computer responded. Was HAL, the all-powerful A.I. that controlled the Discovery One spacecraft, really ignoring him? "I'm sorry, Dave," HAL continued. "I'm afraid I can't do that." "What's the problem?" Dave asked. I've forgotten how to open them."