{"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/deep-learning-for-pedestrians-backpropagation","title":"Deep learning for pedestrians: backpropagation in CNNs","arxiv_id":"1811.11987","date":"2018-11-29","proceeding":null,"authors":["Laurent Boué"],"abstract":"The goal of this document is to provide a pedagogical introduction to the\nmain concepts underpinning the training of deep neural networks using gradient\ndescent; a process known as backpropagation. Although we focus on a very\ninfluential class of architectures called \"convolutional neural networks\"\n(CNNs) the approach is generic and useful to the machine learning community as\na whole. Motivated by the observation that derivations of backpropagation are\noften obscured by clumsy index-heavy narratives that appear somewhat\nmathemagical, we aim to offer a conceptually clear, vectorized description that\narticulates well the higher level logic. Following the principle of \"writing is\nnature's way of letting you know how sloppy your thinking is\", we try to make\nthe calculations meticulous, self-contained and yet as intuitive as possible.\nTaking nothing for granted, ample illustrations serve as visual guides and an\nextensive bibliography is provided for further explorations.\n  (For the sake of clarity, long mathematical derivations and visualizations\nhave been broken up into short \"summarized views\" and longer \"detailed views\"\nencoded into the PDF as optional content groups. Some figures contain\nanimations designed to illustrate important concepts in a more engaging style.\nFor these reasons, we advise to download the document locally and open it using\nAdobe Acrobat Reader. Other viewers were not tested and may not render the\ndetailed views, animations correctly.)","url_abs":"http://arxiv.org/abs/1811.11987v1","url_pdf":"http://arxiv.org/pdf/1811.11987v1.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":"deep-learning-for-pedestrians-backpropagation","repo_url":"https://github.com/Ranlot/backpropagation-CNNs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}