An insect-inspired model for visual binding II: functional analysis and visual attention

Brandon D. Northcutt, Charles M. Higgins

Research output: Research - peer-reviewArticle

Abstract

We have developed a neural network model capable of performing visual binding inspired by neuronal circuitry in the optic glomeruli of flies: a brain area that lies just downstream of the optic lobes where early visual processing is performed. This visual binding model is able to detect objects in dynamic image sequences and bind together their respective characteristic visual features—such as color, motion, and orientation—by taking advantage of their common temporal fluctuations. Visual binding is represented in the form of an inhibitory weight matrix which learns over time which features originate from a given visual object. In the present work, we show that information represented implicitly in this weight matrix can be used to explicitly count the number of objects present in the visual image, to enumerate their specific visual characteristics, and even to create an enhanced image in which one particular object is emphasized over others, thus implementing a simple form of visual attention. Further, we present a detailed analysis which reveals the function and theoretical limitations of the visual binding network and in this context describe a novel network learning rule which is optimized for visual binding.

LanguageEnglish (US)
Pages207-227
Number of pages21
JournalBiological Cybernetics
Volume111
Issue number2
DOIs
StatePublished - Apr 1 2017

Fingerprint

Insects
Weights and Measures
Functional analysis
Optics
Neural Networks (Computer)
Diptera
Color
Learning
Brain
Neural networks
Processing

Keywords

  • Artificial intelligence
  • Blind source separation
  • Neural networks
  • Object perception
  • Visual attention
  • Visual binding

ASJC Scopus subject areas

  • Biotechnology
  • Computer Science(all)

Cite this

An insect-inspired model for visual binding II : functional analysis and visual attention. / Northcutt, Brandon D.; Higgins, Charles M.

In: Biological Cybernetics, Vol. 111, No. 2, 01.04.2017, p. 207-227.

Research output: Research - peer-reviewArticle

@article{25fbc192ab364f81a52a5cd458fce619,
title = "An insect-inspired model for visual binding II: functional analysis and visual attention",
abstract = "We have developed a neural network model capable of performing visual binding inspired by neuronal circuitry in the optic glomeruli of flies: a brain area that lies just downstream of the optic lobes where early visual processing is performed. This visual binding model is able to detect objects in dynamic image sequences and bind together their respective characteristic visual features—such as color, motion, and orientation—by taking advantage of their common temporal fluctuations. Visual binding is represented in the form of an inhibitory weight matrix which learns over time which features originate from a given visual object. In the present work, we show that information represented implicitly in this weight matrix can be used to explicitly count the number of objects present in the visual image, to enumerate their specific visual characteristics, and even to create an enhanced image in which one particular object is emphasized over others, thus implementing a simple form of visual attention. Further, we present a detailed analysis which reveals the function and theoretical limitations of the visual binding network and in this context describe a novel network learning rule which is optimized for visual binding.",
keywords = "Artificial intelligence, Blind source separation, Neural networks, Object perception, Visual attention, Visual binding",
author = "Northcutt, {Brandon D.} and Higgins, {Charles M.}",
year = "2017",
month = "4",
doi = "10.1007/s00422-017-0716-z",
volume = "111",
pages = "207--227",
journal = "Biological Cybernetics",
issn = "0340-1200",
publisher = "Springer Verlag",
number = "2",

}

TY - JOUR

T1 - An insect-inspired model for visual binding II

T2 - Biological Cybernetics

AU - Northcutt,Brandon D.

AU - Higgins,Charles M.

PY - 2017/4/1

Y1 - 2017/4/1

N2 - We have developed a neural network model capable of performing visual binding inspired by neuronal circuitry in the optic glomeruli of flies: a brain area that lies just downstream of the optic lobes where early visual processing is performed. This visual binding model is able to detect objects in dynamic image sequences and bind together their respective characteristic visual features—such as color, motion, and orientation—by taking advantage of their common temporal fluctuations. Visual binding is represented in the form of an inhibitory weight matrix which learns over time which features originate from a given visual object. In the present work, we show that information represented implicitly in this weight matrix can be used to explicitly count the number of objects present in the visual image, to enumerate their specific visual characteristics, and even to create an enhanced image in which one particular object is emphasized over others, thus implementing a simple form of visual attention. Further, we present a detailed analysis which reveals the function and theoretical limitations of the visual binding network and in this context describe a novel network learning rule which is optimized for visual binding.

AB - We have developed a neural network model capable of performing visual binding inspired by neuronal circuitry in the optic glomeruli of flies: a brain area that lies just downstream of the optic lobes where early visual processing is performed. This visual binding model is able to detect objects in dynamic image sequences and bind together their respective characteristic visual features—such as color, motion, and orientation—by taking advantage of their common temporal fluctuations. Visual binding is represented in the form of an inhibitory weight matrix which learns over time which features originate from a given visual object. In the present work, we show that information represented implicitly in this weight matrix can be used to explicitly count the number of objects present in the visual image, to enumerate their specific visual characteristics, and even to create an enhanced image in which one particular object is emphasized over others, thus implementing a simple form of visual attention. Further, we present a detailed analysis which reveals the function and theoretical limitations of the visual binding network and in this context describe a novel network learning rule which is optimized for visual binding.

KW - Artificial intelligence

KW - Blind source separation

KW - Neural networks

KW - Object perception

KW - Visual attention

KW - Visual binding

UR - http://www.scopus.com/inward/record.url?scp=85015712005&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015712005&partnerID=8YFLogxK

U2 - 10.1007/s00422-017-0716-z

DO - 10.1007/s00422-017-0716-z

M3 - Article

VL - 111

SP - 207

EP - 227

JO - Biological Cybernetics

JF - Biological Cybernetics

SN - 0340-1200

IS - 2

ER -