{"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/hyperentm-evolving-scalable-neural-turing","title":"HyperENTM: Evolving Scalable Neural Turing Machines through HyperNEAT","arxiv_id":"1710.04748","date":"2017-10-12","proceeding":null,"authors":["Jakob Merrild","Mikkel Angaju Rasmussen","Sebastian Risi"],"abstract":"Recent developments within memory-augmented neural networks have solved\nsequential problems requiring long-term memory, which are intractable for\ntraditional neural networks. However, current approaches still struggle to\nscale to large memory sizes and sequence lengths. In this paper we show how\naccess to memory can be encoded geometrically through a HyperNEAT-based Neural\nTuring Machine (HyperENTM). We demonstrate that using the indirect HyperNEAT\nencoding allows for training on small memory vectors in a bit-vector copy task\nand then applying the knowledge gained from such training to speed up training\non larger size memory vectors. Additionally, we demonstrate that in some\ninstances, networks trained to copy bit-vectors of size 9 can be scaled to\nsizes of 1,000 without further training. While the task in this paper is\nsimple, these results could open up the problems amendable to networks with\nexternal memories to problems with larger memory vectors and theoretically\nunbounded memory sizes.","url_abs":"http://arxiv.org/abs/1710.04748v1","url_pdf":"http://arxiv.org/pdf/1710.04748v1.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":"hyperentm-evolving-scalable-neural-turing","repo_url":"https://github.com/kalanzai/ENTM_CSharpPort","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}