Long Bai, Shugeng Chen, Peng Wang, He Chen, Jiaqing Yan, Xiaojian Zhu, Enming Song, Bobo Tian, Jiacan Su, Xiaoli Li
{"title":"DeepSeek or ChatGPT: Can brain-computer interfaces/brain-inspired computing achieve leapfrog development with large AI models?","authors":"Long Bai, Shugeng Chen, Peng Wang, He Chen, Jiaqing Yan, Xiaojian Zhu, Enming Song, Bobo Tian, Jiacan Su, Xiaoli Li","doi":"10.1002/brx2.70021","DOIUrl":null,"url":null,"abstract":"<p>Large language models, including DeepSeek and ChatGPT, have the potential to significantly advance brain-computer interfaces and brain-inspired computing by enhancing the accuracy of brain signal decoding and optimizing user interaction. In brain-computer interfaces, these models facilitate more precise and responsive communication, while in brain-inspired computing, they enable realistic simulation of neural networks and improved hardware energy efficiency. However, substantial challenges remain, particularly in healthcare applications and other broader fields.\n <figure>\n <div><picture>\n <source></source></picture><p></p>\n </div>\n </figure></p>","PeriodicalId":94303,"journal":{"name":"Brain-X","volume":"3 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/brx2.70021","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Brain-X","FirstCategoryId":"1085","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/brx2.70021","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Large language models, including DeepSeek and ChatGPT, have the potential to significantly advance brain-computer interfaces and brain-inspired computing by enhancing the accuracy of brain signal decoding and optimizing user interaction. In brain-computer interfaces, these models facilitate more precise and responsive communication, while in brain-inspired computing, they enable realistic simulation of neural networks and improved hardware energy efficiency. However, substantial challenges remain, particularly in healthcare applications and other broader fields.