{"title":"Large-scale foundation models and generative AI for BigData neuroscience.","authors":"Ran Wang, Zhe Sage Chen","doi":"10.1016/j.neures.2024.06.003","DOIUrl":null,"url":null,"abstract":"<p><p>Recent advances in machine learning have led to revolutionary breakthroughs in computer games, image and natural language understanding, and scientific discovery. Foundation models and large-scale language models (LLMs) have recently achieved human-like intelligence thanks to BigData. With the help of self-supervised learning (SSL) and transfer learning, these models may potentially reshape the landscapes of neuroscience research and make a significant impact on the future. Here we present a mini-review on recent advances in foundation models and generative AI models as well as their applications in neuroscience, including natural language and speech, semantic memory, brain-machine interfaces (BMIs), and data augmentation. We argue that this paradigm-shift framework will open new avenues for many neuroscience research directions and discuss the accompanying challenges and opportunities.</p>","PeriodicalId":19146,"journal":{"name":"Neuroscience Research","volume":" ","pages":""},"PeriodicalIF":2.4000,"publicationDate":"2024-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Neuroscience Research","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1016/j.neures.2024.06.003","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"NEUROSCIENCES","Score":null,"Total":0}
引用次数: 0
Abstract
Recent advances in machine learning have led to revolutionary breakthroughs in computer games, image and natural language understanding, and scientific discovery. Foundation models and large-scale language models (LLMs) have recently achieved human-like intelligence thanks to BigData. With the help of self-supervised learning (SSL) and transfer learning, these models may potentially reshape the landscapes of neuroscience research and make a significant impact on the future. Here we present a mini-review on recent advances in foundation models and generative AI models as well as their applications in neuroscience, including natural language and speech, semantic memory, brain-machine interfaces (BMIs), and data augmentation. We argue that this paradigm-shift framework will open new avenues for many neuroscience research directions and discuss the accompanying challenges and opportunities.
期刊介绍:
The international journal publishing original full-length research articles, short communications, technical notes, and reviews on all aspects of neuroscience
Neuroscience Research is an international journal for high quality articles in all branches of neuroscience, from the molecular to the behavioral levels. The journal is published in collaboration with the Japan Neuroscience Society and is open to all contributors in the world.