Zobrazeno 1 - 10
of 90
pro vyhledávání: '"La Higuera, Colin"'
Autor:
Marzouk, Reda, de La Higuera, Colin
Thanks to its solid theoretical foundation, the SHAP framework is arguably one the most widely utilized frameworks for local explainability of ML models. Despite its popularity, its exact computation is known to be very challenging, proven to be NP-H
Externí odkaz:
http://arxiv.org/abs/2405.02936
Autor:
Marzouk, Reda, de La Higuera, Colin
The primary use of any probabilistic model involving a set of random variables is to run inference and sampling queries on it. Inference queries in classical probabilistic models is concerned by the computation of marginal or conditional probabilitie
Externí odkaz:
http://arxiv.org/abs/2206.12862
Autor:
Marzouk, Reda, de la Higuera, Colin
The need of interpreting Deep Learning (DL) models has led, during the past years, to a proliferation of works concerned by this issue. Among strategies which aim at shedding some light on how information is represented internally in DL models, one c
Externí odkaz:
http://arxiv.org/abs/2004.00478
A classical problem in grammatical inference is to identify a language from a set of examples. In this paper, we address the problem of identifying a union of languages from examples that belong to several different unknown languages. Indeed, decompo
Externí odkaz:
http://arxiv.org/abs/1812.08269
Publikováno v:
Notre Dame J. Formal Logic 60, no. 1 (2019), 13-26
We exhibit a family of computably enumerable sets which can be learned within polynomial resource bounds given access only to a teacher, but which requires exponential resources to be learned given access only to a membership oracle. In general, we c
Externí odkaz:
http://arxiv.org/abs/1504.03623
Probabilistic context-free grammars (PCFGs) are used to define distributions over strings, and are powerful modelling tools in a number of areas, including natural language processing, software engineering, model checking, bio-informatics, and patter
Externí odkaz:
http://arxiv.org/abs/1407.1513
Autor:
Beros, Achilles, de la Higuera, Colin
We prove the existence of a canonical form for semi-deterministic transducers with incomparable sets of output strings. Based on this, we develop an algorithm which learns semi-deterministic transducers given access to translation queries. We also pr
Externí odkaz:
http://arxiv.org/abs/1405.2476
Publikováno v:
In Pattern Recognition February 2015 48(2):302-316
