1 Citation (Scopus)

Abstract

Over the years the Artificial Intelligence (AI) community has produced several datasets which have given the machine learning algorithms the opportunity to learn various skills across various domains. However, a subclass of these machine learning algorithms that aimed at learning logic programs, namely the Inductive Logic Programming algorithms, have often failed at the task due to the vastness of these datasets. This has impacted the usability of knowledge representation and reasoning techniques in the development of AI systems. In this research, we try to address this scalability issue for the algorithms that learn answer set programs. We present a sound and complete algorithm which takes the input in a slightly different manner and performs an efficient and more user controlled search for a solution. We show via experiments that our algorithm can learn from two popular datasets from machine learning community, namely bAbl (a question answering dataset) and MNIST (a dataset for handwritten digit recognition), which to the best of our knowledge was not previously possible. The system is publicly available at https://goo.gl/KdWAcV.

Original languageEnglish (US)
Pages (from-to)623-637
Number of pages15
JournalTheory and Practice of Logic Programming
Volume18
Issue number3-4
DOIs
StatePublished - Jul 1 2018

Fingerprint

Answer Sets
Distinct
Learning systems
Machine Learning
Learning algorithms
Artificial intelligence
Learning Algorithm
Artificial Intelligence
Handwritten Digit Recognition
Knowledge Representation and Reasoning
Inductive logic programming (ILP)
Inductive Logic Programming
Question Answering
Knowledge representation
Logic Programs
Usability
Scalability
Acoustic waves
Learning
Experiment

Keywords

  • Answer Set Programming
  • Context Dependent Learning
  • Handwritten Digit Recognition
  • Inductive Logic Programming
  • Question Answering

ASJC Scopus subject areas

  • Software
  • Theoretical Computer Science
  • Hardware and Architecture
  • Computational Theory and Mathematics
  • Artificial Intelligence

Cite this

Incremental and Iterative Learning of Answer Set Programs from Mutually Distinct Examples. / Mitra, Arindam; Baral, Chitta.

In: Theory and Practice of Logic Programming, Vol. 18, No. 3-4, 01.07.2018, p. 623-637.

Research output: Contribution to journalArticle

@article{0d687350e7b746ae9b576a5337b8a549,
title = "Incremental and Iterative Learning of Answer Set Programs from Mutually Distinct Examples",
abstract = "Over the years the Artificial Intelligence (AI) community has produced several datasets which have given the machine learning algorithms the opportunity to learn various skills across various domains. However, a subclass of these machine learning algorithms that aimed at learning logic programs, namely the Inductive Logic Programming algorithms, have often failed at the task due to the vastness of these datasets. This has impacted the usability of knowledge representation and reasoning techniques in the development of AI systems. In this research, we try to address this scalability issue for the algorithms that learn answer set programs. We present a sound and complete algorithm which takes the input in a slightly different manner and performs an efficient and more user controlled search for a solution. We show via experiments that our algorithm can learn from two popular datasets from machine learning community, namely bAbl (a question answering dataset) and MNIST (a dataset for handwritten digit recognition), which to the best of our knowledge was not previously possible. The system is publicly available at https://goo.gl/KdWAcV.",
keywords = "Answer Set Programming, Context Dependent Learning, Handwritten Digit Recognition, Inductive Logic Programming, Question Answering",
author = "Arindam Mitra and Chitta Baral",
year = "2018",
month = "7",
day = "1",
doi = "10.1017/S1471068418000248",
language = "English (US)",
volume = "18",
pages = "623--637",
journal = "Theory and Practice of Logic Programming",
issn = "1471-0684",
publisher = "Cambridge University Press",
number = "3-4",

}

TY - JOUR

T1 - Incremental and Iterative Learning of Answer Set Programs from Mutually Distinct Examples

AU - Mitra, Arindam

AU - Baral, Chitta

PY - 2018/7/1

Y1 - 2018/7/1

N2 - Over the years the Artificial Intelligence (AI) community has produced several datasets which have given the machine learning algorithms the opportunity to learn various skills across various domains. However, a subclass of these machine learning algorithms that aimed at learning logic programs, namely the Inductive Logic Programming algorithms, have often failed at the task due to the vastness of these datasets. This has impacted the usability of knowledge representation and reasoning techniques in the development of AI systems. In this research, we try to address this scalability issue for the algorithms that learn answer set programs. We present a sound and complete algorithm which takes the input in a slightly different manner and performs an efficient and more user controlled search for a solution. We show via experiments that our algorithm can learn from two popular datasets from machine learning community, namely bAbl (a question answering dataset) and MNIST (a dataset for handwritten digit recognition), which to the best of our knowledge was not previously possible. The system is publicly available at https://goo.gl/KdWAcV.

AB - Over the years the Artificial Intelligence (AI) community has produced several datasets which have given the machine learning algorithms the opportunity to learn various skills across various domains. However, a subclass of these machine learning algorithms that aimed at learning logic programs, namely the Inductive Logic Programming algorithms, have often failed at the task due to the vastness of these datasets. This has impacted the usability of knowledge representation and reasoning techniques in the development of AI systems. In this research, we try to address this scalability issue for the algorithms that learn answer set programs. We present a sound and complete algorithm which takes the input in a slightly different manner and performs an efficient and more user controlled search for a solution. We show via experiments that our algorithm can learn from two popular datasets from machine learning community, namely bAbl (a question answering dataset) and MNIST (a dataset for handwritten digit recognition), which to the best of our knowledge was not previously possible. The system is publicly available at https://goo.gl/KdWAcV.

KW - Answer Set Programming

KW - Context Dependent Learning

KW - Handwritten Digit Recognition

KW - Inductive Logic Programming

KW - Question Answering

UR - http://www.scopus.com/inward/record.url?scp=85051374043&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85051374043&partnerID=8YFLogxK

U2 - 10.1017/S1471068418000248

DO - 10.1017/S1471068418000248

M3 - Article

AN - SCOPUS:85051374043

VL - 18

SP - 623

EP - 637

JO - Theory and Practice of Logic Programming

JF - Theory and Practice of Logic Programming

SN - 1471-0684

IS - 3-4

ER -