{"pk":29869,"title":"Disentangling Generativity in Visual Cognition","subtitle":null,"abstract":"Human knowledge is generative: from everyday learning people extract latent features that can recombine to producenew imagined forms. This ability is critical to cognition, but its computational bases remain elusive. Recent researchwith -regularized Variational Autoencoders (-VAE) suggests that generativity in visual cognition may depend on learningdisentangled (localist) feature representations. We tested this proposal by training -VAEs and standard autoencoders toreconstruct bitmaps showing a single object varying in shape, size, location, and color, and manipulating hyperparame-ters to produce differentially-entangled feature representations. These models showed variable generativity, with somestandard autoencoders capable of near-perfect reconstruction of 43 trillion images after training on just 2000. However,constrained -VAEs were unable to reconstruct images reflecting feature combinations which were systematically withheldduring training (e.g. all blue circles). Thus, deep auto-encoders may provide a promising tool for understanding visualgenerativity and potentially other aspects of visual cognition.","language":"eng","license":{"name":"","short_name":"","text":null,"url":""},"keywords":[],"section":"Poster Session 2","is_remote":true,"remote_url":"https://escholarship.org/uc/item/5nd9k6hw","frozenauthors":[{"first_name":"Declan","middle_name":"","last_name":"Campbell","name_suffix":"","institution":"University of Wisconsin – Madison","department":""},{"first_name":"Timothy","middle_name":"","last_name":"Rogers","name_suffix":"","institution":"University of Wisconsin – Madison","department":""}],"date_submitted":null,"date_accepted":null,"date_published":"2020-01-01T18:00:00Z","render_galley":null,"galleys":[{"label":"PDF","type":"pdf","path":"https://journalpub.escholarship.org/cognitivesciencesociety/article/29869/galley/19723/download/"}]}