INTERVIEW: Solving AI amnesia with bee brains

SBS News In Depth

AI systems can do amazing things, but they can sometimes suffer from a drawback called “catastrophic forgetting”. Researchers at Arizona State University hope to learn how to solve the problem by probing the brains of sleeping bees. The pay-off could be more reliable, more memory-efficient artificial intelligence. When AI systems learn one task — say, how to recognize dogs — and are later trained on a new task — like identifying cars — they often forget the first thing they learned. This is called ctastrophic forgetting. Ted Pavlic is an associate professor of computer science and engineering in the School of Computing and Augmented Intelligence, part of the Ira A. Fulton Schools of Engineering at ASU, with a joint appointment in the School of Life Sciences. He leads a unique interdisciplinary research project that blends biology and computer science.