{"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/deep-networks-with-internal-selective","title":"Deep Networks with Internal Selective Attention through Feedback Connections","arxiv_id":"1407.3068","date":"2014-07-11","proceeding":"NeurIPS 2014 12","authors":["Marijn Stollenga","Jonathan Masci","Faustino Gomez","Juergen Schmidhuber"],"abstract":"Traditional convolutional neural networks (CNN) are stationary and\nfeedforward. They neither change their parameters during evaluation nor use\nfeedback from higher to lower layers. Real brains, however, do. So does our\nDeep Attention Selective Network (dasNet) architecture. DasNets feedback\nstructure can dynamically alter its convolutional filter sensitivities during\nclassification. It harnesses the power of sequential processing to improve\nclassification performance, by allowing the network to iteratively focus its\ninternal attention on some of its convolutional filters. Feedback is trained\nthrough direct policy search in a huge million-dimensional parameter space,\nthrough scalable natural evolution strategies (SNES). On the CIFAR-10 and\nCIFAR-100 datasets, dasNet outperforms the previous state-of-the-art model.","url_abs":"http://arxiv.org/abs/1407.3068v2","url_pdf":"http://arxiv.org/pdf/1407.3068v2.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":[],"tasks":[{"task_slug":"deep-attention","task_name":"Deep Attention"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"Deep Networks with Internal Selective Attention through Feedback Connections","rank_in_archive_order":199,"of":265,"metrics":{"Percentage correct":"90.8"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}