Neural network modeling supports a theory on the hierarchical control of prehension

Fan Gao, Mark Latash, Vladimir M. Zatsiorsky

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

A theory on the hierarchical organization of the control of human prehension (grasping and manipulation of a hand-held object) was tested by comparing the performances of neural networks of different designs. The inputs into the networks were external torque, handle width, and thumb location, and the outputs were the individual digit forces. The networks differed only in their architecture: Nl was a classical three-layer network; N2 was a hierarchical two-tier network with single projections, in which the outputs of the first tier were used as inputs for the second tier, that yielded the individual digit forces; and N3 was a hierarchical two-tier network with dual projections, where the inputs to the second tier were the outputs of the first tier-as in N2-plus the inputs into the first tier (external torque, handle width, and thumb location). Each tier of N2 and N 3 consisted of one three-layer network. The N3 network showed the best performance, supporting the idea that the control of prehension is hierarchically organized.

Original languageEnglish (US)
Pages (from-to)352-359
Number of pages8
JournalNeural Computing and Applications
Volume13
Issue number4
DOIs
StatePublished - Dec 1 2004

Fingerprint

Network layers
Torque
Neural networks

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Cite this

@article{babdec8f6427401f96c683f8ee05b0cb,
title = "Neural network modeling supports a theory on the hierarchical control of prehension",
abstract = "A theory on the hierarchical organization of the control of human prehension (grasping and manipulation of a hand-held object) was tested by comparing the performances of neural networks of different designs. The inputs into the networks were external torque, handle width, and thumb location, and the outputs were the individual digit forces. The networks differed only in their architecture: Nl was a classical three-layer network; N2 was a hierarchical two-tier network with single projections, in which the outputs of the first tier were used as inputs for the second tier, that yielded the individual digit forces; and N3 was a hierarchical two-tier network with dual projections, where the inputs to the second tier were the outputs of the first tier-as in N2-plus the inputs into the first tier (external torque, handle width, and thumb location). Each tier of N2 and N 3 consisted of one three-layer network. The N3 network showed the best performance, supporting the idea that the control of prehension is hierarchically organized.",
author = "Fan Gao and Mark Latash and Zatsiorsky, {Vladimir M.}",
year = "2004",
month = "12",
day = "1",
doi = "10.1007/s00521-004-0430-3",
language = "English (US)",
volume = "13",
pages = "352--359",
journal = "Neural Computing and Applications",
issn = "0941-0643",
publisher = "Springer London",
number = "4",

}

Neural network modeling supports a theory on the hierarchical control of prehension. / Gao, Fan; Latash, Mark; Zatsiorsky, Vladimir M.

In: Neural Computing and Applications, Vol. 13, No. 4, 01.12.2004, p. 352-359.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Neural network modeling supports a theory on the hierarchical control of prehension

AU - Gao, Fan

AU - Latash, Mark

AU - Zatsiorsky, Vladimir M.

PY - 2004/12/1

Y1 - 2004/12/1

N2 - A theory on the hierarchical organization of the control of human prehension (grasping and manipulation of a hand-held object) was tested by comparing the performances of neural networks of different designs. The inputs into the networks were external torque, handle width, and thumb location, and the outputs were the individual digit forces. The networks differed only in their architecture: Nl was a classical three-layer network; N2 was a hierarchical two-tier network with single projections, in which the outputs of the first tier were used as inputs for the second tier, that yielded the individual digit forces; and N3 was a hierarchical two-tier network with dual projections, where the inputs to the second tier were the outputs of the first tier-as in N2-plus the inputs into the first tier (external torque, handle width, and thumb location). Each tier of N2 and N 3 consisted of one three-layer network. The N3 network showed the best performance, supporting the idea that the control of prehension is hierarchically organized.

AB - A theory on the hierarchical organization of the control of human prehension (grasping and manipulation of a hand-held object) was tested by comparing the performances of neural networks of different designs. The inputs into the networks were external torque, handle width, and thumb location, and the outputs were the individual digit forces. The networks differed only in their architecture: Nl was a classical three-layer network; N2 was a hierarchical two-tier network with single projections, in which the outputs of the first tier were used as inputs for the second tier, that yielded the individual digit forces; and N3 was a hierarchical two-tier network with dual projections, where the inputs to the second tier were the outputs of the first tier-as in N2-plus the inputs into the first tier (external torque, handle width, and thumb location). Each tier of N2 and N 3 consisted of one three-layer network. The N3 network showed the best performance, supporting the idea that the control of prehension is hierarchically organized.

UR - http://www.scopus.com/inward/record.url?scp=11144274479&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=11144274479&partnerID=8YFLogxK

U2 - 10.1007/s00521-004-0430-3

DO - 10.1007/s00521-004-0430-3

M3 - Article

VL - 13

SP - 352

EP - 359

JO - Neural Computing and Applications

JF - Neural Computing and Applications

SN - 0941-0643

IS - 4

ER -