{"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/attentional-neural-network-feature-selection","title":"Attentional Neural Network: Feature Selection Using Cognitive Feedback","arxiv_id":"1411.5140","date":"2014-11-19","proceeding":"NeurIPS 2014 12","authors":["Qian Wang","Jiaxing Zhang","Sen Song","Zheng Zhang"],"abstract":"Attentional Neural Network is a new framework that integrates top-down\ncognitive bias and bottom-up feature extraction in one coherent architecture.\nThe top-down influence is especially effective when dealing with high noise or\ndifficult segmentation problems. Our system is modular and extensible. It is\nalso easy to train and cheap to run, and yet can accommodate complex behaviors.\nWe obtain classification accuracy better than or competitive with state of art\nresults on the MNIST variation dataset, and successfully disentangle overlaid\ndigits with high success rates. We view such a general purpose framework as an\nessential foundation for a larger system emulating the cognitive abilities of\nthe whole brain.","url_abs":"http://arxiv.org/abs/1411.5140v1","url_pdf":"http://arxiv.org/pdf/1411.5140v1.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":"attentional-neural-network-feature-selection","repo_url":"https://github.com/qianwangthu/feedback-nips2014-wq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"feature-selection","task_name":"feature selection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1411.5140","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}