{"pk":28106,"title":"Learning Hierarchical Visual Representations in Deep Neural NetworksUsing Hierarchical Linguistic Labels","subtitle":null,"abstract":"Modern convolutional neural networks (CNNs) are able toachieve human-level object classification accuracy on specifictasks, and currently outperform competing models in explain-ing complex human visual representations. However, the cate-gorization problem is posed differently for these networks thanfor humans: the accuracy of these networks is evaluated bytheir ability to identify single labels assigned to each image.These labels often cut arbitrarily across natural psychologi-cal taxonomies (e.g., dogs are separated into breeds, but neverjointly categorized as “dogs”), and bias the resulting represen-tations. By contrast, it is common for children to hear bothdog and Dalmatian to describe the same stimulus, helping togroup perceptually disparate objects (e.g., breeds) into a com-mon mental class. In this work, we train CNN classifiers withmultiple labels for each image that correspond to different lev-els of abstraction, and use this framework to reproduce classicpatterns that appear in human generalization behavior.","language":"eng","license":{"name":"","short_name":"","text":null,"url":""},"keywords":[],"section":"Publication-based-Talks","is_remote":true,"remote_url":"https://escholarship.org/uc/item/60d5x5sf","frozenauthors":[{"first_name":"Joshua","middle_name":"","last_name":"Peterson","name_suffix":"","institution":"UC Berkley","department":""},{"first_name":"Paul","middle_name":"","last_name":"Soulos","name_suffix":"","institution":"UC Berkley","department":""},{"first_name":"Aida","middle_name":"","last_name":"Nematzadeh","name_suffix":"","institution":"UC Berkley","department":""},{"first_name":"Thomas","middle_name":"L","last_name":"Grifitsh","name_suffix":"","institution":"UC Berkley","department":""}],"date_submitted":null,"date_accepted":null,"date_published":"2018-01-01T18:00:00Z","render_galley":null,"galleys":[{"label":"PDF","type":"pdf","path":"https://journalpub.escholarship.org/cognitivesciencesociety/article/28106/galley/17759/download/"}]}