{"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/parametric-matrix-models","title":"Parametric Matrix Models","arxiv_id":"2401.11694","date":"2024-01-22","proceeding":null,"authors":["Patrick Cook","Danny Jammooa","Morten Hjorth-Jensen","Daniel D. Lee","Dean Lee"],"abstract":"We present a general class of machine learning algorithms called parametric matrix models. In contrast with most existing machine learning models that imitate the biology of neurons, parametric matrix models use matrix equations that emulate physical systems. Similar to how physics problems are usually solved, parametric matrix models learn the governing equations that lead to the desired outputs. Parametric matrix models can be efficiently trained from empirical data, and the equations may use algebraic, differential, or integral relations. While originally designed for scientific computing, we prove that parametric matrix models are universal function approximators that can be applied to general machine learning problems. After introducing the underlying theory, we apply parametric matrix models to a series of different challenges that show their performance for a wide range of problems. For all the challenges tested here, parametric matrix models produce accurate results within an efficient and interpretable computational framework that allows for input feature extrapolation.","url_abs":"https://arxiv.org/abs/2401.11694v6","url_pdf":"https://arxiv.org/pdf/2401.11694v6.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":[],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-emnist-balanced","task":"Image Classification","dataset":"EMNIST-Balanced","model":"Convolutional PMM (Parametric Matrix Model)","rank_in_archive_order":12,"of":20,"metrics":{"Accuracy":"85.95","Trainable Parameters":"349172"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-emnist-balanced","task":"Image Classification","dataset":"EMNIST-Balanced","model":"PMM (Parametric Matrix Model)","rank_in_archive_order":16,"of":20,"metrics":{"Accuracy":"81.57","Trainable Parameters":"13792"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-fashion-mnist","task":"Image Classification","dataset":"Fashion-MNIST","model":"Convolutional PMM (Parametric Matrix Model)","rank_in_archive_order":17,"of":34,"metrics":{"Accuracy":"90.89","Percentage error":"9.11","Trainable Parameters":"278280"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-fashion-mnist","task":"Image Classification","dataset":"Fashion-MNIST","model":"PMM (Parametric Matrix Model)","rank_in_archive_order":21,"of":34,"metrics":{"Accuracy":"88.58","Percentage error":"11.42","Trainable Parameters":"16744"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-mnist","task":"Image Classification","dataset":"MNIST","model":"Convolutional PMM (Parametric Matrix Model)","rank_in_archive_order":48,"of":81,"metrics":{"Accuracy":"98.99","Percentage error":"1.01","Trainable Parameters":"129416"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-mnist","task":"Image Classification","dataset":"MNIST","model":"PMM (Parametric Matrix Model)","rank_in_archive_order":58,"of":81,"metrics":{"Accuracy":"97.38","Percentage error":"2.62","Trainable Parameters":"4990"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}