{"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/recursive-construction-of-stable-assemblies","title":"RNNs of RNNs: Recursive Construction of Stable Assemblies of Recurrent Neural Networks","arxiv_id":"2106.08928","date":"2021-06-16","proceeding":null,"authors":["Leo Kozachkov","Michaela Ennis","Jean-Jacques Slotine"],"abstract":"Recurrent neural networks (RNNs) are widely used throughout neuroscience as models of local neural activity. Many properties of single RNNs are well characterized theoretically, but experimental neuroscience has moved in the direction of studying multiple interacting areas, and RNN theory needs to be likewise extended. We take a constructive approach towards this problem, leveraging tools from nonlinear control theory and machine learning to characterize when combinations of stable RNNs will themselves be stable. Importantly, we derive conditions which allow for massive feedback connections between interacting RNNs. We parameterize these conditions for easy optimization using gradient-based techniques, and show that stability-constrained \"networks of networks\" can perform well on challenging sequential-processing benchmark tasks. Altogether, our results provide a principled approach towards understanding distributed, modular function in the brain.","url_abs":"https://arxiv.org/abs/2106.08928v6","url_pdf":"https://arxiv.org/pdf/2106.08928v6.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":"recursive-construction-of-stable-assemblies","repo_url":"https://github.com/ennisthemennis/sparse-combo-net","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"sequential-image-classification","task_name":"Sequential Image Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/sequential-image-classification-on-sequential-1","task":"Sequential Image Classification","dataset":"Sequential CIFAR-10","model":"Sparse Combo Net","rank_in_archive_order":9,"of":13,"metrics":{"Unpermuted Accuracy":"65.72"},"uses_additional_data":false},{"leaderboard":"/sota/sequential-image-classification-on-sequential","task":"Sequential Image Classification","dataset":"Sequential MNIST","model":"Sparse Combo Net","rank_in_archive_order":16,"of":30,"metrics":{"Permuted Accuracy":"96.94"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.08928","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}