Decision-tree algorithms are known to be unstable: small variations in the training set can result in different trees and different predictions for the same validation examples. B...
This paper presents a data oriented approach to modeling the complex computing systems, in which an ensemble of correlation models are discovered to represent the system status. I...
Scaffolding techniques allow human instructors to support novice learners in critical early stages, and to remove that support as expertise grows. This paper describes nAble, an a...
Joseph MacInnes, Stephanie Santosa, Nathan Kronenf...
Noisy probabilistic relational rules are a promising world model representation for several reasons. They are compact and generalize over world instantiations. They are usually in...
In this paper, we study a new research problem of causal discovery from streaming features. A unique characteristic of streaming features is that not all features can be available ...