A Perceptron Reveals the Face of Sex

Neural ComputationPublished 1 November 1995

Michael S. Gray, David T. Lawrence, Beatrice A. Golomb, Terrence J. Sejnowski

DOI10.1162/neco.1995.7.6.1160

Source URL

Citations34

SJR quartileQ1

SJR score0.83

SNIP1.45

TL;DR

It is found that the linear perceptron model can classify sex from facial images with 81% accuracy, compared to 92% accuracy with compression coding on the same data set (Golomb et al. 1991).

Abstract

November 01 1995 A Perceptron Reveals the Face of Sex In Special Collection: CogNet Michael S. Gray, Michael S. Gray Howard Hughes Medical Institute, Computational Neurobiology Laboratory, The Salk Institute for Biological Studies, P.O. Box 85800, San Diego, CA 92186-5800 USA and Departments of Biology and Cognitive Science, University of California, San Diego, La Jolla, CA 92093 USA Search for other works by this author on: This Site Google Scholar David T. Lawrence, David T. Lawrence Howard Hughes Medical Institute, Computational Neurobiology Laboratory, The Salk Institute for Biological Studies, P.O. Box 85800, San Diego, CA 92186-5800 USA and Departments of Biology and Cognitive Science, University of California, San Diego, La Jolla, CA 92093 USA Search for other works by this author on: This Site Google Scholar Beatrice A. Golomb, Beatrice A. Golomb Howard Hughes Medical Institute, Computational Neurobiology Laboratory, The Salk Institute for Biological Studies, P.O. Box 85800, San Diego, CA 92186-5800 USA and Departments of Biology and Cognitive Science, University of California, San Diego, La Jolla, CA 92093 USA Search for other works by this author on: This Site Google Scholar Terrence J. Sejnowski Terrence J. Sejnowski Howard Hughes Medical Institute, Computational Neurobiology Laboratory, The Salk Institute for Biological Studies, P.O. Box 85800, San Diego, CA 92186-5800 USA and Departments of Biology and Cognitive Science, University of California, San Diego, La Jolla, CA 92093 USA Search for other works by this author on: This Site Google Scholar Author and Article Information Michael S. Gray Howard Hughes Medical Institute, Computational Neurobiology Laboratory, The Salk Institute for Biological Studies, P.O. Box 85800, San Diego, CA 92186-5800 USA and Departments of Biology and Cognitive Science, University of California, San Diego, La Jolla, CA 92093 USA David T. Lawrence Howard Hughes Medical Institute, Computational Neurobiology Laboratory, The Salk Institute for Biological Studies, P.O. Box 85800, San Diego, CA 92186-5800 USA and Departments of Biology and Cognitive Science, University of California, San Diego, La Jolla, CA 92093 USA Beatrice A. Golomb Howard Hughes Medical Institute, Computational Neurobiology Laboratory, The Salk Institute for Biological Studies, P.O. Box 85800, San Diego, CA 92186-5800 USA and Departments of Biology and Cognitive Science, University of California, San Diego, La Jolla, CA 92093 USA Terrence J. Sejnowski Howard Hughes Medical Institute, Computational Neurobiology Laboratory, The Salk Institute for Biological Studies, P.O. Box 85800, San Diego, CA 92186-5800 USA and Departments of Biology and Cognitive Science, University of California, San Diego, La Jolla, CA 92093 USA Online Issn: 1530-888X Print Issn: 0899-7667 © 1995 Massachusetts Institute of Technology1995 Neural Computation (1995) 7 (6): 1160–1164. https://doi.org/10.1162/neco.1995.7.6.1160 Cite Icon Cite Permissions Share Icon Share Facebook Twitter LinkedIn MailTo Views Icon Views Article contents Figures & tables Video Audio Supplementary Data Peer Review Search Site Citation Michael S. Gray, David T. Lawrence, Beatrice A. Golomb, Terrence J. Sejnowski; A Perceptron Reveals the Face of Sex. Neural Comput 1995; 7 (6): 1160–1164. doi: https://doi.org/10.1162/neco.1995.7.6.1160 Download citation file: Ris (Zotero) Reference Manager EasyBib Bookends Mendeley Papers EndNote RefWorks BibTex toolbar search Search Dropdown Menu toolbar search search input Search input auto suggest filter your search All ContentAll JournalsNeural Computation Search Advanced Search This content is only available as a PDF. © 1995 Massachusetts Institute of Technology1995 Article PDF first page preview Close Modal You do not currently have access to this content.

Keywords

PsychologyNeuroscience

Neural NetworksNeural networks and principal component analysis: Learning from examples without local minima

1,360 Citations1989Pierre Baldi, Kurt Hornik

The main result is a complete description of the landscape attached to E in terms of principal component analysis, showing that E has a unique minimum corresponding to the projection onto the subspace generated by the first principal vectors of a covariance matrix associated with the training patterns.

Neural Information Processing SystemsSEXNET: A Neural Network Identifies Sex From Human Faces

487 Citations1990Beatrice A. Golomb, David T. Lawrence +1 more

A neural network was trained to discriminate sex in human faces, and performed as well as humans on a set of 90 exemplars, and some SexNet errors mimicked those of humans.

PerceptionSex Discrimination: How Do We Tell the Difference between Male and Female Faces?

417 Citations1993Vicki Bruce, A. Mike Burton +6 more

It appears that the ability to make this most basic of facial categorisations may be multiply determined by a combination of 2-D, 3- D, and textural cues and their interrelationships.

PerceptionWhat's the Difference between Men and Women? Evidence from Facial Measurement

365 Citations1993A. Mike Burton, Vicki Bruce +1 more

The difficulty of deriving a reliable function to distinguish between the sexes is discussed with reference to the development of automatic face-processing programs in machine vision, and it is argued that such systems will need to incorporate an understanding of the stimuli if they are to be effective.

Journal of the Optical Society of America ALow-dimensional representation of faces in higher dimensions of the face space

232 Citations1993Alice J. O’Toole, Kenneth A. Deffenbacher +2 more

Various low-dimensional representations of the faces in the higher dimensions of the face space (i.e., the eigenvectors with smaller eigenvalues) provide better information for face recognition.

Categorization of faces using unsupervised feature extraction

136 Citations1990Michael Kenyatta Fleming, Garrison W. Cottrell

The proposal of G. Cottrell et al. (1987) that their image compression network might be used to extract image features for pattern recognition automatically, is tested by training a neural network to compress 64 face images, spanning 11 subjects, and 13 nonface images.

Neural NetworksA physical system approach to recognition memory for spatially transformed faces

46 Citations1988Alice J. O’Toole, Richard B. Millward +1 more

Recognition memory for familiar and unfamiliar spatial frequency filtered faces was examined using a combination of experiments and computer simulations based on the physical-systems approach to memory to show a significant interaction in recognition performance between the frequency characteristics of the learning and test pictures of the faces.

Biological CyberneticsCaricatural effects in automated face perception

33 Citations1993Roberto Brunelli, Tomaso Poggio

The problem of gender classification and identification is addressed using a geometrical description of faces, extracted automatically from digitized pictures of frontal views of people without facial hair, to perform satisfactorily on the classification tasks and exhibit the phenomenon of caricature.