Neural Information Processing Systems · 1990 · 487 citations · 0 references
ComputingComputer ScienceVision ScienceArtificial IntelligenceComputer VisionMachine LearningDeep LearningFace PerceptionFace RecognitionNeural NetworksPattern RecognitionSex DiscriminationBiological Sex DeterminationFacial Gender PerceptionGender Perception From Facial AppearanceMachine Learning Sex EstimationNeural Network ModelingSex Estimation AccuracySex Estimation Error
Sex identification in animals has biological importance. Humans are good at making this determination visually, but machines have not matched this ability. A neural network was trained to discriminate sex in human faces, and performed as well as humans on a set of 90 exemplars. Images sampled at 30×30 were compressed using a 900×40×900 fully-connected back-propagation network; activities of hidden units served as input to a back-propagation trained to produce values of 1 for male and 0 for female faces. The network's average error rate of 8.1% compared favorably to humans, who averaged 11.6%. Some SexNet errors mimicked those of humans.