Knowledge distillation is the technique of compressing a larger neural network, known as teacher, into smaller student, while still trying to maintain performance network much possible. Existing methods knowledge are mostly applicable for classification tasks. Many them also require access data used train teacher model. To address problem regression tasks under absence original training data, p...

The main result of this paper is that the length of the Wadge hierarchy of omega context-free languages is greater than the Cantor ordinal 0, and the same result holds for the conciliating Wadge hierarchy, de1ned by Duparc (J. Symbolic Logic, to appear), of in1nitary context-free languages, studied by Beauquier (Ph.D. Thesis, Universit9 e Paris 7, 1984). In the course of our proof, we get resul...

Davari, M. 2017. Advances Towards Data-Race-Free Cache Coherence Through Data Classification. Digital Comprehensive Summaries of Uppsala Dissertations from the Faculty of Science and Technology 1521. 64 pp. Uppsala: Acta Universitatis Upsaliensis. ISBN 978-91-554-9925-9. Providing a consistent view of the shared memory based on precise and well-defined semantics —memory consistency model—has be...

Treebanks, such as the Penn Treebank, provide a basis for the automatic creation of broad coverage grammars. In the simplest case, rules can simply be ‘read off’ the parse-annotations of the corpus, producing either a simple or probabilistic context-free grammar. Such grammars, however, can be very large, presenting problems for the subsequent computational costs of parsing under the grammar. I...