Results 21 to 30 of about 9,002 (304)
Clarifying the Notion “Parameter”
Biolinguistics, 2007 This article aims to reflect on linguistic architecture by re-examining language variation. Three progressively deeper forms of variation are suggested, each of which arguably contributes to this exercise in rather different ways.
Juan Uriagereka
doaj +1 more source
Learnability of quantified formulas
Theoretical Computer Science, 1999 zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Víctor Dalmau, Peter Jeavons 0001
openaire +3 more sources
Learnability of automatic classes
Journal of Computer and System Sciences, 2010 zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Sanjay Jain 0001 +2 more
openaire +2 more sources
Information and Computation, 2012 zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Sanjay Jain 0001 +2 more
openaire +3 more sources
The Credit Problem in parametric stress: A probabilistic approach
Glossa, 2021 In this paper, we introduce a novel domain-general, statistical learning model for P&P grammars: the Expectation Driven Parameter Learner (EDPL). We show that the EDPL provides a mathematically principled solution to the Credit Problem (Dresher 1999). We
Aleksei Ioulevitch Nazarov, Gaja Jarosz
doaj +2 more sources
The learnability of gender agreement in Spanish bilinguals
, 2020 Achieving high levels of proficiency in a second language (L2) represents a great challenge. One of the domains where second language learners show persistent difficulties is morphosyntax, and specifically grammatical gender.
Dias P., Costello B., Caffarra S.
core +1 more source
Two negations for the price of one
Glossa, 2016 Standard English is typically described as a double negation language. In double negation languages, each negative marker contributes independent semantic force. Two negations in the same clause usually cancel each other out, resulting in an affirmative
Anna Notley +3 more
doaj +2 more sources
On the learnability of vector spaces
Journal of Computer and System Sciences, 2002 zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Valentina S. Harizanov +1 more
openaire +2 more sources
The strength of weak learnability [PDF]
Machine Learning, 1989 This paper addresses the problem of improving the accuracy of an hypothesis output by a learning algorithm in the distribution-free (PAC) learning model. A concept class is learnable (or strongly learnable) if, given access to a source of examples of the unknown concept, the learner with high probability is able to output an hypothesis that is correct ...
openaire +3 more sources
On Learnability, Complexity and Stability [PDF]
, 2013 We consider the fundamental question of learnability of a hypotheses class in the supervised learning setting and in the general learning setting introduced by Vladimir Vapnik. We survey classic results characterizing learnability in term of suitable notions of complexity, as well as more recent results that establish the connection between ...
Villa, Silvia +2 more
openaire +3 more sources