Most users of machine-learning products are reluctant to use the systems without any sense of the underlying logic that has led to the system's predictions. Unfortunately many...
We introduce a new method of adaptive routing on k-ary n-cubes, Globally Adaptive Load-Balance (GAL). GAL makes global routing decisions using global information. In contrast, most...
Arjun Singh, William J. Dally, Brian Towles, Amit ...
In this paper, we propose a distributed solution to the problem of configuring classifier trees in distributed stream mining systems. The configuration involves selecting appro...
Hyunggon Park, Deepak S. Turaga, Olivier Verscheur...
—We propose a new parametric class of scheduling and routing policies for open multiclass queueing networks. We establish their stability and show they are amenable to distribute...
Ioannis Ch. Paschalidis, Chang Su, Michael Caraman...
This paper describes a new model for extracting large-field optical flow patterns to generate distributed representations of neural activation to control complex visual tasks such ...