{"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/on-the-derivatives-of-feed-forward-neural-1","title":"On the derivatives of feed-forward neural networks","arxiv_id":"2005.07039","date":"2020-05-12","proceeding":null,"authors":["Rabah Abdul Khalek","Valerio Bertone"],"abstract":"In this paper we present a C++ implementation of the analytic derivative of a feed-forward neural network with respect to its free parameters for an arbitrary architecture, known as back-propagation. We dubbed this code NNAD (Neural Network Analytic Derivatives) and interfaced it with the widely-used ceres-solver minimiser to fit neural networks to pseudodata in two different least-squares problems. The first is a direct fit of Legendre polynomials. The second is a somewhat more involved minimisation problem where the function to be fitted takes part in an integral. Finally, using a consistent framework, we assess the efficiency of our analytic derivative formula as compared to numerical and automatic differentiation as provided by ceres-solver. We thus demonstrate the advantage of using NNAD in problems involving both deep or shallow neural networks.","url_abs":"http://arxiv.org/abs/2005.07039v1","url_pdf":"http://arxiv.org/pdf/2005.07039v1.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"on-the-derivatives-of-feed-forward-neural-1","repo_url":"https://github.com/rabah-khalek/NNAD","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"on-the-derivatives-of-feed-forward-neural-1","repo_url":"https://github.com/rabah-khalek/NNAD-Interface","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}