New Metrics and Experimental Paradigms for Continual Learning

Tyler L. Hayes, Ronald Kemker, Nathan D. Cahill, Christopher Kanan
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
In order for a robotic agent to learn successfully in an uncontrolled environment, it must be able to immediately alter its behavior. Deep neural networks are the dominant approach for classification tasks in computer vision, but typical algorithms and architectures are incapable of immediately learning new tasks without catastrophically forgetting previously acquired knowledge. There has been renewed interest in solving this problem, but there are limitations to existing solutions, including
more » ... or performance compared to offline models, large memory footprints, and learning slowly. In this abstract, we formalize the continual learning paradigm and propose new benchmarks for assessing continual learning agents.
doi:10.1109/cvprw.2018.00273 dblp:conf/cvpr/HayesKCK18 fatcat:25j6v7hmzfcalie6vov5dlukvq