ELSC Seminar Series

Lifelong Learning is the cutting edge of artificial intelligence – encompassing computational methods that allow systems to learn in runtime and incorporate learning for application in new, unanticipated situations. Until recently, this sort of computation has been found exclusively in nature; thus, Lifelong Learning looks to nature for its underlying principles and mechanisms and then transfer them to this new technology.

Yet SOTA Lifelong Learning, like classical learning, is limited in its accuracy for temporal prediction from short and incomplete measurements. This is where our new technology appears. The technology is based on a new type of neural networks, where much like the brain, the connections between neurons are no longer scalar numbers, but rather temporal functions. This gives the networks an unparallel capacity, strong temporal accuracy, and ability to keep effectivity even when most measurements are lost.  Interestingly, our temporally changing network while more capable, is smaller in size and consumes significantly less power. A version used for Reinforcement learning and control is under development.