In this paper we propose a new algorithm for learning polyhedral classifiers. In contrast to existing methods for learning polyhedral classifier which solve a constrained optimiza...
d Abstractions for Contract Validation Guido de Caso, Víctor Braberman, Diego Garbervetsky and Sebastián Uchitel —Pre/post condition-based specifications are common-place in a...
Methods for cleaning up (or recognizing) states of a neural network are crucial for the functioning of many neural cognitive models. For example, Vector Symbolic Architectures pro...
Terrence C. Stewart, Yichuan Tang, Chris Eliasmith
Abstract. We present a method to specify software for a special kind of safetycritical embedded systems, where sensors deliver low-level values that must be abstracted and pre-proc...
Device firmware is a piece of concurrent software that achieves high performance at the cost of software complexity. They contain subtle race conditions that make them difficult t...