We transform the outputs of each hidden neuron in a multi-layer perceptron network to have zero output and zero slope on average, and use separate shortcut connections to model th...
This document contains supplementary material to the article ‘Statistical test for consistent estimation of causal effects in linear non-Gaussian models’, AISTATS 2012. A tabl...
The traditional representation of a program is as a linear sequence of text. At some stage in the execution sequence the source text is checked for type correctness and its transla...
Ronald Morrison, Richard C. H. Connor, Quintin I. ...
This paper presents a new program logic designed for facilitating automated reasoning about pointer programs. The program logic is directly inspired by previous work by O'Hea...
Java(X) is a framework for type refinement. It extends Java's type language with annotations drawn from an algebra X and structural subtyping in terms of the annotations. Each...