SRI International to focus in biological memory in AI applications under DARPA L2M program
MENLO PARK, Calif. Defense Advanced Research Projects Agency (DARPA) officials selected SRI International to develop a next-generation artificial intelligence (AI) system able to learn continuously and apply that learning to become better and more reliable at performing new tasks. The contract will be supported under DARPA’s Lifelong Learning Machines (L2M) Program.
As part of the L2M program, SRI researchers will develop AI algorithms based on biological mechanisms in memory consolidation and replay. With this AI technology, future cognitive systems such as autonomous robots may be able to continually learn after initial deployment, improving execution performance and overall safety.
Biological memory transfer is a complex sequence of dynamic processes, with local and global synchronization patterns. These processes support memories with flexibility in expression for future thinking, foresight, planning, and creativity. While AI systems have become core to many commercial and government applications, they are not able to handle new scenarios that they are not trained on. Even with retraining, today’s systems are prone to “catastrophic forgetting” when a new item disrupts previously learned knowledge.
“Our goal is to address these limitations by enabling AI systems to know what to learn and when,” explains Sek Chai, Ph.D., technical director in the Center for Vision Technologies, SRI International. “Since memory is a key element of cognitive function, our research is focused on understanding and applying biological memory transfers to new AI algorithms that can fundamentally improve their performance throughout their fielded lifetime experience.”