{"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-particle-swarm-optimization-based-flexible","title":"A Particle Swarm Optimization-based Flexible Convolutional Auto-Encoder for Image Classification","arxiv_id":"1712.05042","date":"2017-12-13","proceeding":null,"authors":["Yanan Sun","Bing Xue","Mengjie Zhang","Gary G. Yen"],"abstract":"Convolutional auto-encoders have shown their remarkable performance in\nstacking to deep convolutional neural networks for classifying image data\nduring past several years. However, they are unable to construct the\nstate-of-the-art convolutional neural networks due to their intrinsic\narchitectures. In this regard, we propose a flexible convolutional auto-encoder\nby eliminating the constraints on the numbers of convolutional layers and\npooling layers from the traditional convolutional auto-encoder. We also design\nan architecture discovery method by using particle swarm optimization, which is\ncapable of automatically searching for the optimal architectures of the\nproposed flexible convolutional auto-encoder with much less computational\nresource and without any manual intervention. We use the designed architecture\noptimization algorithm to test the proposed flexible convolutional auto-encoder\nthrough utilizing one graphic processing unit card on four extensively used\nimage classification datasets. Experimental results show that our work in this\npaper significantly outperform the peer competitors including the\nstate-of-the-art algorithm.","url_abs":"http://arxiv.org/abs/1712.05042v2","url_pdf":"http://arxiv.org/pdf/1712.05042v2.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-particle-swarm-optimization-based-flexible","repo_url":"https://github.com/yn-sun/evocae","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"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":"https://app.syntology.ai/?focus=1712.05042","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}