482 citations · 509 across the 2 of their papers we have counts for
2 papers
cs.LG2015★ 482 cited
Imaging Time-Series to Improve Classification and Imputation
Zhiguang Wang, Tim Oates
Inspired by recent successes of deep learning in computer vision, we propose a novel framework for encoding time series as different types of images, namely, Gramian Angular Summat…
cs.LG2012★ 27 cited
The Thing That We Tried Didn't Work Very Well : Deictic Representation in Reinforcement Learning
Sarah Finney, Natalia Gardiol, Leslie Pack Kaelbling +1
Most reinforcement learning methods operate on propositional representations of the world state. Such representations are often intractably large and generalize poorly. Using a dei…