{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/binding-via-reconstruction-clustering","title":"Binding via Reconstruction Clustering","arxiv_id":"1511.06418","date":"2015-11-19","proceeding":null,"authors":["Klaus Greff","Rupesh Kumar Srivastava","Jürgen Schmidhuber"],"abstract":"Disentangled distributed representations of data are desirable for machine\nlearning, since they are more expressive and can generalize from fewer\nexamples. However, for complex data, the distributed representations of\nmultiple objects present in the same input can interfere and lead to\nambiguities, which is commonly referred to as the binding problem. We argue for\nthe importance of the binding problem to the field of representation learning,\nand develop a probabilistic framework that explicitly models inputs as a\ncomposition of multiple objects. We propose an unsupervised algorithm that uses\ndenoising autoencoders to dynamically bind features together in multi-object\ninputs through an Expectation-Maximization-like clustering process. The\neffectiveness of this method is demonstrated on artificially generated datasets\nof binary images, showing that it can even generalize to bind together new\nobjects never seen by the autoencoder during training.","url_abs":"http://arxiv.org/abs/1511.06418v4","url_pdf":"http://arxiv.org/pdf/1511.06418v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"binding-via-reconstruction-clustering","repo_url":"https://github.com/Qwlouse/Binding","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1511.06418","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}