Academic Journal
View in EDS

Hypothesizing an algorithm from one example: the role of specificity.

Bibliographic Details
Title: Hypothesizing an algorithm from one example: the role of specificity.
Authors: Muggleton FREng, S. H.
Source: Philosophical Transactions of the Royal Society A: Mathematical, Physical & Engineering Sciences; 7/24/2023, Vol. 381 Issue 2251, p1-15, 15p
Subject Terms: Statistical learning, Artificial intelligence, Machine learning, Learning, Algorithms, Stereo vision (Computer science)
Abstract: Statistical machine learning usually achieves high-accuracy models by employing tens of thousands of examples. By contrast, both children and adult humans typically learn new concepts from either one or a small number of instances. The high data efficiency of human learning is not easily explained in terms of standard formal frameworks for machine learning, including Gold's learning-in-the-limit framework and Valiant's probably approximately correct (PAC) model. This paper explores ways in which this apparent disparity between human and machine learning can be reconciled by considering algorithms involving a preference for specificity combined with program minimality. It is shown how this can be efficiently enacted using hierarchical search based on identification of certificates and push-down automata to support hypothesizing compactly expressed maximal efficiency algorithms. Early results of a new system called DeepLog indicate that such approaches can support efficient top-down construction of relatively complex logic programs from a single example. This article is part of a discussion meeting issue 'Cognitive artificial intelligence'. [ABSTRACT FROM AUTHOR]
Copyright of Philosophical Transactions of the Royal Society A: Mathematical, Physical & Engineering Sciences is the property of Royal Society and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Complementary Index
FullText Text:
  Availability: 0
Header DbId: edb
DbLabel: Complementary Index
An: 164082372
RelevancyScore: 938
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 937.8671875
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Hypothesizing an algorithm from one example: the role of specificity.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Muggleton+FREng%2C+S%2E+H%2E%22">Muggleton FREng, S. H.</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: Philosophical Transactions of the Royal Society A: Mathematical, Physical & Engineering Sciences; 7/24/2023, Vol. 381 Issue 2251, p1-15, 15p
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Statistical+learning%22">Statistical learning</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+intelligence%22">Artificial intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Learning%22">Learning</searchLink><br /><searchLink fieldCode="DE" term="%22Algorithms%22">Algorithms</searchLink><br /><searchLink fieldCode="DE" term="%22Stereo+vision+%28Computer+science%29%22">Stereo vision (Computer science)</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Statistical machine learning usually achieves high-accuracy models by employing tens of thousands of examples. By contrast, both children and adult humans typically learn new concepts from either one or a small number of instances. The high data efficiency of human learning is not easily explained in terms of standard formal frameworks for machine learning, including Gold's learning-in-the-limit framework and Valiant's probably approximately correct (PAC) model. This paper explores ways in which this apparent disparity between human and machine learning can be reconciled by considering algorithms involving a preference for specificity combined with program minimality. It is shown how this can be efficiently enacted using hierarchical search based on identification of certificates and push-down automata to support hypothesizing compactly expressed maximal efficiency algorithms. Early results of a new system called DeepLog indicate that such approaches can support efficient top-down construction of relatively complex logic programs from a single example. This article is part of a discussion meeting issue 'Cognitive artificial intelligence'. [ABSTRACT FROM AUTHOR]
– Name: Abstract
  Label:
  Group: Ab
  Data: <i>Copyright of Philosophical Transactions of the Royal Society A: Mathematical, Physical & Engineering Sciences is the property of Royal Society and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edb&AN=164082372
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1098/rsta.2022.0046
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 15
        StartPage: 1
    Subjects:
      – SubjectFull: Statistical learning
        Type: general
      – SubjectFull: Artificial intelligence
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Learning
        Type: general
      – SubjectFull: Algorithms
        Type: general
      – SubjectFull: Stereo vision (Computer science)
        Type: general
    Titles:
      – TitleFull: Hypothesizing an algorithm from one example: the role of specificity.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Muggleton FREng, S. H.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 24
              M: 07
              Text: 7/24/2023
              Type: published
              Y: 2023
          Identifiers:
            – Type: issn-print
              Value: 1364503X
          Numbering:
            – Type: volume
              Value: 381
            – Type: issue
              Value: 2251
          Titles:
            – TitleFull: Philosophical Transactions of the Royal Society A: Mathematical, Physical & Engineering Sciences
              Type: main
ResultId 1