{"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/a-genetic-programming-approach-to-designing","title":"A Genetic Programming Approach to Designing Convolutional Neural Network Architectures","arxiv_id":"1704.00764","date":"2017-04-03","proceeding":null,"authors":["Masanori Suganuma","Shinichi Shirakawa","Tomoharu Nagao"],"abstract":"The convolutional neural network (CNN), which is one of the deep learning\nmodels, has seen much success in a variety of computer vision tasks. However,\ndesigning CNN architectures still requires expert knowledge and a lot of trial\nand error. In this paper, we attempt to automatically construct CNN\narchitectures for an image classification task based on Cartesian genetic\nprogramming (CGP). In our method, we adopt highly functional modules, such as\nconvolutional blocks and tensor concatenation, as the node functions in CGP.\nThe CNN structure and connectivity represented by the CGP encoding method are\noptimized to maximize the validation accuracy. To evaluate the proposed method,\nwe constructed a CNN architecture for the image classification task with the\nCIFAR-10 dataset. The experimental result shows that the proposed method can be\nused to automatically find the competitive CNN architecture compared with\nstate-of-the-art models.","url_abs":"http://arxiv.org/abs/1704.00764v2","url_pdf":"http://arxiv.org/pdf/1704.00764v2.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":"a-genetic-programming-approach-to-designing","repo_url":"https://github.com/sg-nm/cgp-cnn","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-genetic-programming-approach-to-designing","repo_url":"https://github.com/SourangshuGhosh/CGP-CNN-Design","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-genetic-programming-approach-to-designing","repo_url":"https://github.com/TabishA/cgpunet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"a-genetic-programming-approach-to-designing","repo_url":"https://github.com/gmontamat/gentun","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"a-genetic-programming-approach-to-designing","repo_url":"https://github.com/pdefraene/cgp_cnn_predictors","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1704.00764","atlas_url":"https://app.syntology.ai/?focus=1704.00764","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}