The use of Chaos Game Representation (CGR) or its generalization, Universal Sequence Maps (USM), to describe the distribution of biological sequences has been found objectionable ...
We describe a system that successfully transfers value function knowledge across multiple subdomains of realtime strategy games in the context of multiagent reinforcement learning....
Searching approximate nearest neighbors in large scale high dimensional data set has been a challenging problem. This paper presents a novel and fast algorithm for learning binary...
An important class of image data sets depict an object undergoing deformation. When there are only a few underlying causes of the deformation, these images have a natural lowdimen...
A common way to represent a time series is to divide it into shortduration blocks, each of which is then represented by a set of basis functions. A limitation of this approach, ho...