{"pk":28717,"title":"Extracting and Utilizing Abstract, Structured Representations for Analogy","subtitle":null,"abstract":"Human analogical ability involves the re-use of abstract, struc-tured representations within and across domains. Here, wepresent a generative neural network that completes analogiesin a 1D metric space, without explicit training on analogy.Our model integrates two key ideas. First, it operates overrepresentations inspired by properties of the mammalian En-torhinal Cortex (EC), believed to extract low-dimensional rep-resentations of the environment from the transition probabil-ities between states. Second, we show that a neural networkequipped with a simple predictive objective and highly generalinductive bias can learn to utilize these EC-like codes to com-pute explicit, abstract relations between pairs of objects. Theproposed inductive bias favors a latent code that consists ofanti-correlated representations. The relational representationslearned by the model can then be used to complete analogiesinvolving the signed distance between novel input pairs (1:3:: 5:? (7)), and extrapolate outside of the network’s trainingdomain. As a proof of principle, we extend the same architec-ture to more richly structured tree representations. We suggestthat this combination of predictive, error-driven learning andsimple inductive biases offers promise for deriving and utiliz-ing the representations necessary for high-level cognitive func-tions, such as analogy.","language":"eng","license":{"name":"","short_name":"","text":null,"url":""},"keywords":[{"word":"abstract structured representations; analogy; neu-ral networks; predictive learning; relational reasoning;"}],"section":"Papers with Poster Presentations","is_remote":true,"remote_url":"https://escholarship.org/uc/item/2c79n8v2","frozenauthors":[{"first_name":"Steven","middle_name":"M.","last_name":"Frankland","name_suffix":"","institution":"Princeton University","department":""},{"first_name":"Taylor","middle_name":"W.","last_name":"Webb","name_suffix":"","institution":"Princeton University","department":""},{"first_name":"Alexander","middle_name":"A.","last_name":"Petrov","name_suffix":"","institution":"The Ohio State University","department":""},{"first_name":"Randall","middle_name":"C.","last_name":"O’Reilly","name_suffix":"","institution":"University of California, Davis","department":""},{"first_name":"Jonathan","middle_name":"D.","last_name":"Cohen","name_suffix":"","institution":"Princeton University","department":""}],"date_submitted":null,"date_accepted":null,"date_published":"2019-01-01T18:00:00Z","render_galley":null,"galleys":[{"label":"PDF","type":"pdf","path":"https://journalpub.escholarship.org/cognitivesciencesociety/article/28717/galley/18588/download/"}]}