{"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/about-pyramid-structure-in-convolutional","title":"About Pyramid Structure in Convolutional Neural Networks","arxiv_id":"1608.04064","date":"2016-08-14","proceeding":null,"authors":["Ihsan Ullah","Alfredo Petrosino"],"abstract":"Deep convolutional neural networks (CNN) brought revolution without any doubt\nto various challenging tasks, mainly in computer vision. However, their model\ndesigning still requires attention to reduce number of learnable parameters,\nwith no meaningful reduction in performance. In this paper we investigate to\nwhat extend CNN may take advantage of pyramid structure typical of biological\nneurons. A generalized statement over convolutional layers from input till\nfully connected layer is introduced that helps further in understanding and\ndesigning a successful deep network. It reduces ambiguity, number of\nparameters, and their size on disk without degrading overall accuracy.\nPerformance are shown on state-of-the-art models for MNIST, Cifar-10,\nCifar-100, and ImageNet-12 datasets. Despite more than 80% reduction in\nparameters for Caffe_LENET, challenging results are obtained. Further, despite\n10-20% reduction in training data along with 10-40% reduction in parameters for\nAlexNet model and its variations, competitive results are achieved when\ncompared to similar well-engineered deeper architectures.","url_abs":"http://arxiv.org/abs/1608.04064v1","url_pdf":"http://arxiv.org/pdf/1608.04064v1.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":"about-pyramid-structure-in-convolutional","repo_url":"https://github.com/Adi-repo/Capstone_Project_2020","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"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}