Solving Tangram puzzles

A connectionist approach

Kemal Oflazer

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

We present a connectionist approach for solving Tangram puzzles. Tangram is an ancient Chinese puzzle where the object is to decompose a given figure into seven basic geometric figures. One connectionist approach models Tangram pieces and their possible placements and orientations as connectionist neuron units which receive excitatory connections from input units defining the puzzle and lateral inhibitory connections from competing or conflicting units. The network of these connectionist units, operating as a Boltzmann Machine, relaxes into a configuration in which units defining the solution receive no inhibitory input from other units. We present results from an implementation of our model using the Rochester Connectionist Simulator.

Original languageEnglish
Pages (from-to)603-616
Number of pages14
JournalInternational Journal of Intelligent Systems
Volume8
Issue number5
Publication statusPublished - Jun 1993
Externally publishedYes

Fingerprint

Tangram
Unit
Neurons
Simulators
Figure
Boltzmann Machine
Placement
Neuron
Lateral
Simulator
Decompose
Configuration

ASJC Scopus subject areas

  • Artificial Intelligence
  • Control and Systems Engineering

Cite this

Solving Tangram puzzles : A connectionist approach. / Oflazer, Kemal.

In: International Journal of Intelligent Systems, Vol. 8, No. 5, 06.1993, p. 603-616.

Research output: Contribution to journalArticle

@article{28aba47d03fb46b1bd18bda27b11a869,
title = "Solving Tangram puzzles: A connectionist approach",
abstract = "We present a connectionist approach for solving Tangram puzzles. Tangram is an ancient Chinese puzzle where the object is to decompose a given figure into seven basic geometric figures. One connectionist approach models Tangram pieces and their possible placements and orientations as connectionist neuron units which receive excitatory connections from input units defining the puzzle and lateral inhibitory connections from competing or conflicting units. The network of these connectionist units, operating as a Boltzmann Machine, relaxes into a configuration in which units defining the solution receive no inhibitory input from other units. We present results from an implementation of our model using the Rochester Connectionist Simulator.",
author = "Kemal Oflazer",
year = "1993",
month = "6",
language = "English",
volume = "8",
pages = "603--616",
journal = "International Journal of Intelligent Systems",
issn = "0884-8173",
publisher = "John Wiley and Sons Ltd",
number = "5",

}

TY - JOUR

T1 - Solving Tangram puzzles

T2 - A connectionist approach

AU - Oflazer, Kemal

PY - 1993/6

Y1 - 1993/6

N2 - We present a connectionist approach for solving Tangram puzzles. Tangram is an ancient Chinese puzzle where the object is to decompose a given figure into seven basic geometric figures. One connectionist approach models Tangram pieces and their possible placements and orientations as connectionist neuron units which receive excitatory connections from input units defining the puzzle and lateral inhibitory connections from competing or conflicting units. The network of these connectionist units, operating as a Boltzmann Machine, relaxes into a configuration in which units defining the solution receive no inhibitory input from other units. We present results from an implementation of our model using the Rochester Connectionist Simulator.

AB - We present a connectionist approach for solving Tangram puzzles. Tangram is an ancient Chinese puzzle where the object is to decompose a given figure into seven basic geometric figures. One connectionist approach models Tangram pieces and their possible placements and orientations as connectionist neuron units which receive excitatory connections from input units defining the puzzle and lateral inhibitory connections from competing or conflicting units. The network of these connectionist units, operating as a Boltzmann Machine, relaxes into a configuration in which units defining the solution receive no inhibitory input from other units. We present results from an implementation of our model using the Rochester Connectionist Simulator.

UR - http://www.scopus.com/inward/record.url?scp=0027615381&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027615381&partnerID=8YFLogxK

M3 - Article

VL - 8

SP - 603

EP - 616

JO - International Journal of Intelligent Systems

JF - International Journal of Intelligent Systems

SN - 0884-8173

IS - 5

ER -