Modeling unsupervised perceptual category learning

Brenden Lake, Gautam K. Vallabha, James L. McClelland

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

During the learning of speech sounds and other perceptual categories, category labels are not provided, the number of categories is unknown, and the stimuli are encountered sequentially. These constraints provide a challenge for models, but they have been recently addressed in the Online Mixture Estimation model of unsupervised vowel category learning [1]. the model treats categories as Gaussian distributions, proposing both the number and parameters of the categories. while the model has been shown to successfully learn vowel categories, it has not been evaluated as a model of the learning process. We account for three results regarding the learning process: Infants' discrimination of speech sounds is better after exposure to a bimodal rather than unimodal distribution [2], infants' discrimination of vowels is affected by acoustic distance [3], and subjects place category centers near frequent stimuli in an unsupervised visual classification task [4].

Original languageEnglish (US)
Title of host publication2008 IEEE 7th International Conference on Development and Learning, ICDL
Pages25-30
Number of pages6
DOIs
StatePublished - 2008
Event2008 IEEE 7th International Conference on Development and Learning, ICDL - Monterey, CA, United States
Duration: Aug 9 2008Aug 12 2008

Other

Other2008 IEEE 7th International Conference on Development and Learning, ICDL
CountryUnited States
CityMonterey, CA
Period8/9/088/12/08

Fingerprint

Learning
Phonetics
learning
Acoustic waves
Normal Distribution
Acoustics
Gaussian distribution
learning process
infant
stimulus
discrimination
Labels
acoustics
Discrimination (Psychology)

ASJC Scopus subject areas

  • Developmental Biology
  • Computer Science(all)
  • Biomedical Engineering
  • Education

Cite this

Lake, B., Vallabha, G. K., & McClelland, J. L. (2008). Modeling unsupervised perceptual category learning. In 2008 IEEE 7th International Conference on Development and Learning, ICDL (pp. 25-30). [4640800] https://doi.org/10.1109/DEVLRN.2008.4640800

Modeling unsupervised perceptual category learning. / Lake, Brenden; Vallabha, Gautam K.; McClelland, James L.

2008 IEEE 7th International Conference on Development and Learning, ICDL. 2008. p. 25-30 4640800.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lake, B, Vallabha, GK & McClelland, JL 2008, Modeling unsupervised perceptual category learning. in 2008 IEEE 7th International Conference on Development and Learning, ICDL., 4640800, pp. 25-30, 2008 IEEE 7th International Conference on Development and Learning, ICDL, Monterey, CA, United States, 8/9/08. https://doi.org/10.1109/DEVLRN.2008.4640800
Lake B, Vallabha GK, McClelland JL. Modeling unsupervised perceptual category learning. In 2008 IEEE 7th International Conference on Development and Learning, ICDL. 2008. p. 25-30. 4640800 https://doi.org/10.1109/DEVLRN.2008.4640800
Lake, Brenden ; Vallabha, Gautam K. ; McClelland, James L. / Modeling unsupervised perceptual category learning. 2008 IEEE 7th International Conference on Development and Learning, ICDL. 2008. pp. 25-30
@inproceedings{bc035c43e98f4fb9ab712dda0058e8e3,
title = "Modeling unsupervised perceptual category learning",
abstract = "During the learning of speech sounds and other perceptual categories, category labels are not provided, the number of categories is unknown, and the stimuli are encountered sequentially. These constraints provide a challenge for models, but they have been recently addressed in the Online Mixture Estimation model of unsupervised vowel category learning [1]. the model treats categories as Gaussian distributions, proposing both the number and parameters of the categories. while the model has been shown to successfully learn vowel categories, it has not been evaluated as a model of the learning process. We account for three results regarding the learning process: Infants' discrimination of speech sounds is better after exposure to a bimodal rather than unimodal distribution [2], infants' discrimination of vowels is affected by acoustic distance [3], and subjects place category centers near frequent stimuli in an unsupervised visual classification task [4].",
author = "Brenden Lake and Vallabha, {Gautam K.} and McClelland, {James L.}",
year = "2008",
doi = "10.1109/DEVLRN.2008.4640800",
language = "English (US)",
isbn = "9781424426621",
pages = "25--30",
booktitle = "2008 IEEE 7th International Conference on Development and Learning, ICDL",

}

TY - GEN

T1 - Modeling unsupervised perceptual category learning

AU - Lake, Brenden

AU - Vallabha, Gautam K.

AU - McClelland, James L.

PY - 2008

Y1 - 2008

N2 - During the learning of speech sounds and other perceptual categories, category labels are not provided, the number of categories is unknown, and the stimuli are encountered sequentially. These constraints provide a challenge for models, but they have been recently addressed in the Online Mixture Estimation model of unsupervised vowel category learning [1]. the model treats categories as Gaussian distributions, proposing both the number and parameters of the categories. while the model has been shown to successfully learn vowel categories, it has not been evaluated as a model of the learning process. We account for three results regarding the learning process: Infants' discrimination of speech sounds is better after exposure to a bimodal rather than unimodal distribution [2], infants' discrimination of vowels is affected by acoustic distance [3], and subjects place category centers near frequent stimuli in an unsupervised visual classification task [4].

AB - During the learning of speech sounds and other perceptual categories, category labels are not provided, the number of categories is unknown, and the stimuli are encountered sequentially. These constraints provide a challenge for models, but they have been recently addressed in the Online Mixture Estimation model of unsupervised vowel category learning [1]. the model treats categories as Gaussian distributions, proposing both the number and parameters of the categories. while the model has been shown to successfully learn vowel categories, it has not been evaluated as a model of the learning process. We account for three results regarding the learning process: Infants' discrimination of speech sounds is better after exposure to a bimodal rather than unimodal distribution [2], infants' discrimination of vowels is affected by acoustic distance [3], and subjects place category centers near frequent stimuli in an unsupervised visual classification task [4].

UR - http://www.scopus.com/inward/record.url?scp=67650122399&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67650122399&partnerID=8YFLogxK

U2 - 10.1109/DEVLRN.2008.4640800

DO - 10.1109/DEVLRN.2008.4640800

M3 - Conference contribution

SN - 9781424426621

SP - 25

EP - 30

BT - 2008 IEEE 7th International Conference on Development and Learning, ICDL

ER -