Queries revisited

By Dana Angluin. 2001

241 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Theory and Mathematics

Citations in the corpus

Machine Teaching: An Inverse Problem to Machine Learning and an Approach Toward Optimal Education (2015, background): “Subsequent theoretical developments can be found in e.g. (Zilles et al. 2011; Balbach and Zeugmann 2009; Angluin 2004; Angluin and Krikis 1997; Goldman and Mathias 1996; Mathias 1997; Balbach and Zeugmann 2006; Balbach 2008; Kobayashi and Shinohara 2009; Angluin and Krikis 2003; Rivest and Yin…”
Machine Teaching for Bayesian Learners in the Exponential Family (2013, background): “The classification task is the same as in Figure 1, with x ∈ [0, 1] and y ∈ {−1, 1}.”
A bibliographical study of grammatical inference (2005, background): “It is conjectured (also by Angluin [29]) not to be the case for richer classes.”
Analysis of Perceptron-Based Active Learning (2009, background): “Finally, there is a rich body of theory on a related model in which it is permissible to create query points synthetically; a recent survey by Angluin [1] summarizes key results.”
Crowdsourcing large scale wrapper inference (2014, methodology): “The data extraction technique presented in this paper has been inspired by the seminal work of Dana Angluin [1,2], who addressed the problem of exactly inferring”
Agnostic active learning (2006, background): “The membership-query setting [1,2,13,27] is similar to active learning considered here, except that no unlabeled data is given.”
A bound on the label complexity of agnostic active learning (2007, background): “The interested reader should consult the limpid survey by Angluin [4].”
How Do Humans Teach: On Curriculum Learning and Teaching Dimension (2011, background): “The first thread, developed by the computational learning theory community, is exemplified by the “teaching dimension” model [9] and its extensions [12, 10, 1, 2, 11, 13, 18].”
A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysis (2019, methodology): “This data-point is then annotated by the oracle(s) (Angluin (2001)), this can be very e ﬃ cient in ﬁnite domains.”
The Teaching Dimension of Linear Learners (2015, background): “(2011); Balbach & Zeugmann (2009); Angluin (2004); Angluin & Krikis (1997); Goldman & Mathias (1996); Mathias (1997); Balbach & Zeugmann (2006); Balbach (2008); Kobayashi & Shinohara (2009); Angluin & Krikis (2003); Rivest & Yin (1995); Ben-David & Eiron (1998); Doliwa et al.”
Recent Developments in Algorithmic Teaching (2009, methodology): “This is even true for the query learning model introduced by Angluin [1, 2], since the teacher or oracle, though answering truthfully, is assumed to behave adversarially whenever possible.”
Active Learning Literature Survey (2009, background): “Efﬁcient query synthesis is often tractable and efﬁcient for ﬁnite problem domains (Angluin, 2001).”
Teacher Improves Learning by Selecting a Training Subset (2018, background): “The theoretical study of machine teaching has focused on the teaching dimension, i.e. the minimum training set size needed to exactly teach a target concept θ ∗ [20, 38, 46, 18, 29, 45, 16, 44, 48, 9, 3, 4, 21, 31, 8, 7, 25, 5, 36, 23, 10].”
Analysis of a greedy active learning strategy (2004, background): “There has also been some work on creating query points synthetically, including a rich body of theoretical results [1, 2], but this approach suffers from two problems: first, from a practical viewpoint, the queries thus produced can be quite unnatural and therefore bewildering for a human to…”
Mixed-Initiative Active Learning (2012, background): “An important insight is that an active learner can never learn faster than when a passive learner is taught optimally (Goldman & Kearns, 1995; Angluin, 2004).”
Two faces of active learning (2011, background): “1 Some results of active learning theory There is a large body of work on active learning within the membership query model [1] and also some work on active online learning [8].”
Teaching Randomized Learners (2006, background): “Angluin and Kriķis’ [3, 4] model prevents collusion by giving incompatible hypothesis spaces to teacher and learner.”
Rule Extraction from Recurrent Neural Networks: ATaxonomy and Review (2005, methodology): “of models through querying of the underlying system (Angluin, 1981, 1987; Cohn, 1994; MacKay, 1992; Cohn et al., 1994; King et al., 2004; Angluin, 2004).”