{"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-convolutional-neural-network-design","title":"Deep Convolutional Neural Network Design Patterns","arxiv_id":"1611.00847","date":"2016-11-02","proceeding":null,"authors":["Leslie N. Smith","Nicholay Topin"],"abstract":"Recent research in the deep learning field has produced a plethora of new\narchitectures. At the same time, a growing number of groups are applying deep\nlearning to new applications. Some of these groups are likely to be composed of\ninexperienced deep learning practitioners who are baffled by the dizzying array\nof architecture choices and therefore opt to use an older architecture (i.e.,\nAlexnet). Here we attempt to bridge this gap by mining the collective knowledge\ncontained in recent deep learning research to discover underlying principles\nfor designing neural network architectures. In addition, we describe several\narchitectural innovations, including Fractal of FractalNet network, Stagewise\nBoosting Networks, and Taylor Series Networks (our Caffe code and prototxt\nfiles is available at https://github.com/iPhysicist/CNNDesignPatterns). We hope\nothers are inspired to build on our preliminary work.","url_abs":"http://arxiv.org/abs/1611.00847v3","url_pdf":"http://arxiv.org/pdf/1611.00847v3.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-convolutional-neural-network-design","repo_url":"https://github.com/iPhysicist/CNNDesignPatterns","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"fractal-block","method_name":"Fractal Block"},{"method_slug":"fractalnet","method_name":"FractalNet"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}