{"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/swgridnet-a-deep-convolutional-neural-network","title":"SwGridNet: A Deep Convolutional Neural Network based on Grid Topology for Image Classification","arxiv_id":"1709.07646","date":"2017-09-22","proceeding":null,"authors":["Atsushi Takeda"],"abstract":"Deep convolutional neural networks (CNNs) achieve remarkable performance on\nimage classification tasks. Recent studies, however, have demonstrated that\ngeneralization abilities are more important than the depth of neural networks\nfor improving performance on image classification tasks. Herein, a new neural\nnetwork called SwGridNet is proposed. A SwGridNet includes many convolutional\nprocessing units which connect mutually as a grid network where many processing\npaths exist between input and output. A SwGridNet has high generalization\ncapability because the multipath architecture has the same effect of ensemble\nlearning. As described in this paper, details of the SwGridNet network\narchitecture are presented. Experimentally obtained results presented in this\npaper show that SwGridNets respectively achieve test error rates of 2.95% and\n15.67% in a CIFAR-10 and CIFAR-100 classification tasks. The results indicate\nthat the SwGridNet performance approximates that of state-of-the-art deep CNNs.","url_abs":"http://arxiv.org/abs/1709.07646v3","url_pdf":"http://arxiv.org/pdf/1709.07646v3.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":"swgridnet-a-deep-convolutional-neural-network","repo_url":"https://github.com/takedarts/swgridnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"ensemble-learning","task_name":"Ensemble Learning"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}