Abstract. We introduce a mathematical framework for black-box software testing of functional correctness, based on concepts from stochastic process theory. This framework supports ...
Incorporating invariances into a learning algorithm is a common problem in machine learning. We provide a convex formulation which can deal with arbitrary loss functions and arbit...
Choon Hui Teo, Amir Globerson, Sam T. Roweis, Alex...
Approximate linear programming (ALP) offers a promising framework for solving large factored Markov decision processes (MDPs) with both discrete and continuous states. Successful ...
Abstract: In most cases, it is simple inconvenience of use that keeps formal methods from being put to industrial use. This paper argues that functionalities, even though of simple...
This paper introduces GNARL, an evolutionary program which induces recurrent neural networks that are structurally unconstrained. In contrast to constructive and destructive algor...
Gregory M. Saunders, Peter J. Angeline, Jordan B. ...