{"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/an-algorithm-for-routing-vectors-in-sequences","title":"An Algorithm for Routing Vectors in Sequences","arxiv_id":"2211.11754","date":"2022-11-20","proceeding":null,"authors":["Franz A. Heinsen"],"abstract":"We propose a routing algorithm that takes a sequence of vectors and computes a new sequence with specified length and vector size. Each output vector maximizes \"bang per bit,\" the difference between a net benefit to use and net cost to ignore data, by better predicting the input vectors. We describe output vectors as geometric objects, as latent variables that assign credit, as query states in a model of associative memory, and as agents in a model of a Society of Mind. We implement the algorithm with optimizations that reduce parameter count, computation, and memory use by orders of magnitude, enabling us to route sequences of greater length than previously possible. We evaluate our implementation on natural language and visual classification tasks, obtaining competitive or state-of-the-art accuracy and end-to-end credit assignments that are interpretable.","url_abs":"https://arxiv.org/abs/2211.11754v3","url_pdf":"https://arxiv.org/pdf/2211.11754v3.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":"an-algorithm-for-routing-vectors-in-sequences","repo_url":"https://github.com/glassroom/heinsen_routing","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"text-classification","task_name":"Text Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"Heinsen Routing + BEiT-large 16 224","rank_in_archive_order":11,"of":265,"metrics":{"Percentage correct":"99.2"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"Heinsen Routing + BEiT-large 16 224","rank_in_archive_order":7,"of":211,"metrics":{"PARAMS":"309.8M","Percentage correct":"93.8"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"Heinsen Routing + BEiT-large 16 224","rank_in_archive_order":130,"of":1060,"metrics":{"Number of params":"312.8M","Top 1 Accuracy":"86.7%"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-imdb","task":"Sentiment Analysis","dataset":"IMDb","model":"Heinsen Routing + RoBERTa Large","rank_in_archive_order":4,"of":49,"metrics":{"Accuracy":"96.2"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-sst-2-binary","task":"Sentiment Analysis","dataset":"SST-2 Binary classification","model":"Heinsen Routing + RoBERTa-large","rank_in_archive_order":21,"of":87,"metrics":{"Accuracy":"96.0"},"uses_additional_data":true},{"leaderboard":"/sota/sentiment-analysis-on-sst-5-fine-grained","task":"Sentiment Analysis","dataset":"SST-5 Fine-grained classification","model":"Heinsen Routing + RoBERTa Large","rank_in_archive_order":2,"of":31,"metrics":{"Accuracy":"59.8"},"uses_additional_data":false},{"leaderboard":"/sota/text-classification-on-imdb","task":"Text Classification","dataset":"IMDb","model":"Heinsen Routing + RoBERTa-large","rank_in_archive_order":13,"of":13,"metrics":{},"uses_additional_data":true}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}