تقرير
One-Shot Induction of Generalized Logical Concepts via Human Guidance
العنوان: | One-Shot Induction of Generalized Logical Concepts via Human Guidance |
---|---|
المؤلفون: | Das, Mayukh, Ramanan, Nandini, Doppa, Janardhan Rao, Natarajan, Sriraam |
سنة النشر: | 2019 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Artificial Intelligence |
الوصف: | We consider the problem of learning generalized first-order representations of concepts from a single example. To address this challenging problem, we augment an inductive logic programming learner with two novel algorithmic contributions. First, we define a distance measure between candidate concept representations that improves the efficiency of search for target concept and generalization. Second, we leverage richer human inputs in the form of advice to improve the sample-efficiency of learning. We prove that the proposed distance measure is semantically valid and use that to derive a PAC bound. Our experimental analysis on diverse concept learning tasks demonstrates both the effectiveness and efficiency of the proposed approach over a first-order concept learner using only examples. Comment: STARAI '20, Workshop version |
نوع الوثيقة: | Working Paper |
الوصول الحر: | http://arxiv.org/abs/1912.07060Test |
رقم الانضمام: | edsarx.1912.07060 |
قاعدة البيانات: | arXiv |
ResultId |
1 |
---|---|
Header |
edsarx arXiv edsarx.1912.07060 1006 3 Report report 1006.43450927734 |
PLink |
https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsarx&AN=edsarx.1912.07060&custid=s6537998&authtype=sso |
FullText |
Array
(
[Availability] => 0
)
Array ( [0] => Array ( [Url] => http://arxiv.org/abs/1912.07060 [Name] => EDS - Arxiv [Category] => fullText [Text] => View record in Arxiv [MouseOverText] => View record in Arxiv ) ) |
Items |
Array
(
[Name] => Title
[Label] => Title
[Group] => Ti
[Data] => One-Shot Induction of Generalized Logical Concepts via Human Guidance
)
Array ( [Name] => Author [Label] => Authors [Group] => Au [Data] => <searchLink fieldCode="AR" term="%22Das%2C+Mayukh%22">Das, Mayukh</searchLink><br /><searchLink fieldCode="AR" term="%22Ramanan%2C+Nandini%22">Ramanan, Nandini</searchLink><br /><searchLink fieldCode="AR" term="%22Doppa%2C+Janardhan+Rao%22">Doppa, Janardhan Rao</searchLink><br /><searchLink fieldCode="AR" term="%22Natarajan%2C+Sriraam%22">Natarajan, Sriraam</searchLink> ) Array ( [Name] => DatePubCY [Label] => Publication Year [Group] => Date [Data] => 2019 ) Array ( [Name] => Subset [Label] => Collection [Group] => HoldingsInfo [Data] => Computer Science ) Array ( [Name] => Subject [Label] => Subject Terms [Group] => Su [Data] => <searchLink fieldCode="DE" term="%22Computer+Science+-+Artificial+Intelligence%22">Computer Science - Artificial Intelligence</searchLink> ) Array ( [Name] => Abstract [Label] => Description [Group] => Ab [Data] => We consider the problem of learning generalized first-order representations of concepts from a single example. To address this challenging problem, we augment an inductive logic programming learner with two novel algorithmic contributions. First, we define a distance measure between candidate concept representations that improves the efficiency of search for target concept and generalization. Second, we leverage richer human inputs in the form of advice to improve the sample-efficiency of learning. We prove that the proposed distance measure is semantically valid and use that to derive a PAC bound. Our experimental analysis on diverse concept learning tasks demonstrates both the effectiveness and efficiency of the proposed approach over a first-order concept learner using only examples.<br />Comment: STARAI '20, Workshop version ) Array ( [Name] => TypeDocument [Label] => Document Type [Group] => TypDoc [Data] => Working Paper ) Array ( [Name] => URL [Label] => Access URL [Group] => URL [Data] => <link linkTarget="URL" linkTerm="http://arxiv.org/abs/1912.07060" linkWindow="_blank">http://arxiv.org/abs/1912.07060</link> ) Array ( [Name] => AN [Label] => Accession Number [Group] => ID [Data] => edsarx.1912.07060 ) |
RecordInfo |
Array
(
[BibEntity] => Array
(
[Subjects] => Array
(
[0] => Array
(
[SubjectFull] => Computer Science - Artificial Intelligence
[Type] => general
)
)
[Titles] => Array
(
[0] => Array
(
[TitleFull] => One-Shot Induction of Generalized Logical Concepts via Human Guidance
[Type] => main
)
)
)
[BibRelationships] => Array
(
[HasContributorRelationships] => Array
(
[0] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Das, Mayukh
)
)
)
[1] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Ramanan, Nandini
)
)
)
[2] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Doppa, Janardhan Rao
)
)
)
[3] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Natarajan, Sriraam
)
)
)
)
[IsPartOfRelationships] => Array
(
[0] => Array
(
[BibEntity] => Array
(
[Dates] => Array
(
[0] => Array
(
[D] => 15
[M] => 12
[Type] => published
[Y] => 2019
)
)
)
)
)
)
)
|
IllustrationInfo |