BrainNPT：用于脑网络分类的 Transformer 网络预训练【英文版】

英文标题：BrainNPT: Pre-training of Transformer networks for brain network classification中文摘要：本文提出了一种基于 Transformer 的深度学习网络，名为 BrainNPT，用于脑功能网络分类，并探讨了使用未标记数据进行预训练的方法，结果表明使用预训练的 BrainNPT 模型可以显著提高分类表现。英文摘要：Deep learning methods have advanced quickly in brain imaging analysis overthe past few years, but they are usually restricted by the limited labeleddata. Pre-trained model on unlabeled data has presented promising improvementin feature learning in many domains, including natural language processing