Proceedings of the Annual Meeting of the Cognitive Science Society

Human category learning is known to be a function of both the complexity of the category rule and attentionalbias. A classic and critically diagnostic human category problem involves learning integral stimuli (correlated features) using acondensation rule, or separable stimuli (independent features) using a filtration rule. Human category learning shows differentiallearning based on category rules that either require attentional binding or ignoring features. It has been shown that neuralnetworks learning with backpropagation cannot differentially learn or distribute attention without built in perceptual bias. Ineffect neural networks fail to integrate the complexity of learning with the representational bias of the stimuli. In this paper weshow that Deep Learning networks, through successive re-encoding and the development of more sensitive feature detectors,learn both the category rules while modeling the attentional bias consistent with the human performance in a task of categorizingrealistic 3D-modeled faces.