{"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/sets-of-autoencoders-with-shared-latent","title":"Sets of autoencoders with shared latent spaces","arxiv_id":"1811.02373","date":"2018-11-06","proceeding":null,"authors":["Vasily Morzhakov"],"abstract":"Autoencoders receive latent models of input data. It was shown in recent\nworks that they also estimate probability density functions of the input. This\nfact makes using the Bayesian decision theory possible. If we obtain latent\nmodels of input data for each class or for some points in the space of\nparameters in a parameter estimation task, we are able to estimate likelihood\nfunctions for those classes or points in parameter space. We show how the set\nof autoencoders solves the recognition problem. Each autoencoder describes its\nown model or context, a latent vector that presents input data in the latent\nspace may be called treatment in its context. Sharing latent spaces of\nautoencoders gives a very important property that is the ability to separate\ntreatment and context where the input information is treated through the set of\nautoencoders. There are two remarkable and most valuable results of this work:\na mechanism that shows a possible way of forming abstract concepts and a way of\nreducing dataset's size during training. These results are confirmed by tests\npresented in the article.","url_abs":"http://arxiv.org/abs/1811.02373v1","url_pdf":"http://arxiv.org/pdf/1811.02373v1.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":"sets-of-autoencoders-with-shared-latent","repo_url":"https://gitlab.com/Morzhakov/SharedLatentSpace","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"parameter-estimation","task_name":"parameter estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}