DARPA Sets Proposers Day on Lifelong Machine Learning
Automatic and ongoing learning could help driverless vehicles become safer, for instance, and adapt to circumstances they weren't specifically programmed for.
The Defense Advanced Research Projects Agency (DARPA) is hosting a Proposers Day on March 30 about its new Lifelong Learning Machines (L2M) program, a program with the goal of developing next-generation technologies that can learn from new situations and apply that learning to become better and more reliable, while remaining constrained within a predetermined set of limits that the system cannot override. Automatic and ongoing learning could help driverless vehicles become safer, for instance, and adapt to circumstances they weren't specifically programmed for.
"Life is by definition unpredictable. It is impossible for programmers to anticipate every problematic or surprising situation that might arise, which means existing ML systems remain susceptible to failures as they encounter the irregularities and unpredictability of real-world circumstances," said L2M Program Manager Hava Siegelmann. "Today, if you want to extend an ML system's ability to perform in a new kind of situation, you have to take the system out of service and retrain it with additional data sets relevant to that new situation. This approach is just not scalable."
The program staff will host the Proposers Day at the DARPA Conference Center in Arlington, Va.
"Enabling a computer to learn even the simplest things from experience has been a longstanding but elusive goal," Siegelmann said. "That's because today's computers are designed to run on prewritten programs incapable of adapting as they execute, a model that hasn't changed since the British polymath Alan Turing developed the earliest computing machines in the 1930s. L2M calls for a new computing paradigm."