{"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/serket-an-architecture-for-connecting","title":"SERKET: An Architecture for Connecting Stochastic Models to Realize a Large-Scale Cognitive Model","arxiv_id":"1712.00929","date":"2017-12-04","proceeding":null,"authors":["Tomoaki Nakamura","Takayuki Nagai","Tadahiro Taniguchi"],"abstract":"To realize human-like robot intelligence, a large-scale cognitive\narchitecture is required for robots to understand the environment through a\nvariety of sensors with which they are equipped. In this paper, we propose a\nnovel framework named Serket that enables the construction of a large-scale\ngenerative model and its inference easily by connecting sub-modules to allow\nthe robots to acquire various capabilities through interaction with their\nenvironments and others. We consider that large-scale cognitive models can be\nconstructed by connecting smaller fundamental models hierarchically while\nmaintaining their programmatic independence. Moreover, connected modules are\ndependent on each other, and parameters are required to be optimized as a\nwhole. Conventionally, the equations for parameter estimation have to be\nderived and implemented depending on the models. However, it becomes harder to\nderive and implement those of a larger scale model. To solve these problems, in\nthis paper, we propose a method for parameter estimation by communicating the\nminimal parameters between various modules while maintaining their programmatic\nindependence. Therefore, Serket makes it easy to construct large-scale models\nand estimate their parameters via the connection of modules. Experimental\nresults demonstrated that the model can be constructed by connecting modules,\nthe parameters can be optimized as a whole, and they are comparable with the\noriginal models that we have proposed.","url_abs":"http://arxiv.org/abs/1712.00929v3","url_pdf":"http://arxiv.org/pdf/1712.00929v3.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":"serket-an-architecture-for-connecting","repo_url":"https://github.com/naka-lab/Serket","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","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}