Scalable Recollections for Continual Lifelong Learning
national conference on artificial intelligence, 2017.
We have proposed and experimentally validated a general purpose Scalable Recollection Module that is designed to scale for very long time-frames
Given the recent success of Deep Learning applied to a variety of single tasks, it is natural to consider more human-realistic settings. Perhaps the most difficult of these settings is that of continual lifelong learning, where the model must learn online over a continuous stream of non-stationary data. A successful continual lifelong lea...More
PPT (Upload PPT)