{"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/convolutional-neural-networks-in-convolution","title":"Convolutional Neural Networks In Convolution","arxiv_id":"1810.03946","date":"2018-10-09","proceeding":null,"authors":["Xiaobo Huang"],"abstract":"Currently, increasingly deeper neural networks have been applied to improve\ntheir accuracy. In contrast, We propose a novel wider Convolutional Neural\nNetworks (CNN) architecture, motivated by the Multi-column Deep Neural Networks\nand the Network In Network(NIN), aiming for higher accuracy without input data\ntransmutation. In our architecture, namely \"CNN In Convolution\"(CNNIC), a small\nCNN, instead of the original generalized liner model(GLM) based filters, is\nconvoluted as kernel on the original image, serving as feature extracting layer\nof this networks. And further classifications are then carried out by a global\naverage pooling layer and a softmax layer. Dropout and orthonormal\ninitialization are applied to overcome training difficulties including slow\nconvergence and over-fitting. Persuasive classification performance is\ndemonstrated on MNIST.","url_abs":"http://arxiv.org/abs/1810.03946v1","url_pdf":"http://arxiv.org/pdf/1810.03946v1.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":"convolutional-neural-networks-in-convolution","repo_url":"https://github.com/MyWorkShop/Convolutional-Neural-Networks-in-Convolution","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"}],"methods":[{"method_slug":"dropout","method_name":"Dropout"},{"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}