{"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/evaluation-of-convolutional-neural-networks","title":"Evaluation of convolutional neural networks using a large multi-subject P300 dataset","arxiv_id":"2001.04225","date":"2020-01-10","proceeding":null,"authors":[],"abstract":"Deep neural networks (DNN) have been studied in various machine learning\nareas. For example, event-related potential (ERP) signal classification is a\nhighly complex task potentially suitable for DNN as signal-to-noise ratio is\nlow, and underlying spatial and temporal patterns display a large intra- and\nintersubject variability. Convolutional neural networks (CNN) have been\ncompared with baseline traditional models, i.e. linear discriminant analysis\n(LDA) and support vector machines (SVM) for single trial classification using a\nlarge multi-subject publicly available P300 dataset of school-age children (138\nmales and 112 females). For single trial classification, classification\naccuracy stayed between 62% and 64% for all tested classification models. When\napplying the trained classification models to averaged trials, accuracy\nincreased to 76-79% without significant differences among classification\nmodels. CNN did not prove superior to baseline for the tested dataset.\nComparison with related literature, limitations and future directions are\ndiscussed.","url_abs":"http://arxiv.org/abs/2001.04225v1","url_pdf":"http://arxiv.org/pdf/2001.04225v1.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":"evaluation-of-convolutional-neural-networks","repo_url":"https://bitbucket.org/lvareka/cnnforgtn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"erp","task_name":"ERP"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}