{"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/enhanced-image-classification-with-a-fast","title":"Enhanced Image Classification With a Fast-Learning Shallow Convolutional Neural Network","arxiv_id":"1503.04596","date":"2015-03-16","proceeding":null,"authors":["Mark D. McDonnell","Tony Vladusich"],"abstract":"We present a neural network architecture and training method designed to\nenable very rapid training and low implementation complexity. Due to its\ntraining speed and very few tunable parameters, the method has strong potential\nfor applications requiring frequent retraining or online training. The approach\nis characterized by (a) convolutional filters based on biologically inspired\nvisual processing filters, (b) randomly-valued classifier-stage input weights,\n(c) use of least squares regression to train the classifier output weights in a\nsingle batch, and (d) linear classifier-stage output units. We demonstrate the\nefficacy of the method by applying it to image classification. Our results\nmatch existing state-of-the-art results on the MNIST (0.37% error) and\nNORB-small (2.2% error) image classification databases, but with very fast\ntraining times compared to standard deep network approaches. The network's\nperformance on the Google Street View House Number (SVHN) (4% error) database\nis also competitive with state-of-the art methods.","url_abs":"http://arxiv.org/abs/1503.04596v3","url_pdf":"http://arxiv.org/pdf/1503.04596v3.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":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"FLSCNN","rank_in_archive_order":255,"of":265,"metrics":{"Percentage correct":"75.9"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-mnist","task":"Image Classification","dataset":"MNIST","model":"FLSCNN","rank_in_archive_order":28,"of":81,"metrics":{"Percentage error":"0.4"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-svhn","task":"Image Classification","dataset":"SVHN","model":"FLSCNN","rank_in_archive_order":41,"of":62,"metrics":{"Percentage error":"4.0"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}