How Does the Experimental Setting Affect the Conclusions of Neural Encoding Models?
文献类型:会议论文
作者 | Xiaohan Zhang1,3; Shaonan Wang1,3; Chengqing Zong1,2,3 |
出版日期 | 2022 |
会议日期 | 2022 |
会议地点 | Marseille |
英文摘要 | Recent years have witnessed the tendency of neural encoding models on exploring brain language processing using naturalistic stimuli. Neural encoding models are data-driven methods that require an encoding model to investigate the mystery of brain mechanisms hidden in the data. As a data-driven method, the performance of encoding models is very sensitive to the experimental setting. However, it is unknown how the experimental setting further affects the conclusions of neural encoding models. This paper systematically investigated this problem and evaluated the influence of three experimental settings, i.e., the data size, the cross-validation training method, and the statistical testing method. Results demonstrate that inappropriate cross-validation training and small data size can substantially decrease the performance of encoding models, especially in the temporal lobe and the frontal lobe. And different null hypotheses in significance testing lead to highly different significant brain regions. Based on these results, we suggest a block-wise cross-validation training method and an adequate data size for increasing the performance of linear encoding models. We also propose two strict null hypotheses to control false positive discovery rates. |
源URL | [http://ir.ia.ac.cn/handle/173211/52049] |
专题 | 模式识别国家重点实验室_自然语言处理 |
作者单位 | 1.School of Artificial Intelligence, University of Chinese Academy of Sciences 2.CAS Center for Excellence in Brain Science and Intelligence Technology 3.National Laboratory of Pattern Recognition, Institute of Automation, CAS |
推荐引用方式 GB/T 7714 | Xiaohan Zhang,Shaonan Wang,Chengqing Zong. How Does the Experimental Setting Affect the Conclusions of Neural Encoding Models?[C]. 见:. Marseille. 2022. |
入库方式: OAI收割
来源:自动化研究所
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。