Transferring and generalizing deep-learning-based neural encoding models across subjects

• Published in: NeuroImage (Orlando, Fla.) Vol. 176; pp. 152 - 163
• Main Authors: Wen, Haiguang, Shi, Junxing, Chen, Wei, Liu, Zhongming
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.08.2018; Elsevier Limited
• Subjects: Accuracy; Adult; Bayes Theorem; Bayesian analysis; Bayesian inference; Brain; Brain - physiology; Brain mapping; Brain Mapping - methods; Cortex; Datasets; Deep Learning; Distance learning; Female; Functional magnetic resonance imaging; Humans; Incremental learning; Information processing; Magnetic Resonance Imaging; Mathematical models; Natural vision; Neural coding; Neural encoding; Neural networks; Neural Pathways - physiology; Neuroimaging; Pattern Recognition, Visual - physiology; Population studies; Reproducibility of Results; Visual stimuli; Young Adult; Natural vision; Deep learning; Incremental learning; Bayesian inference; Neural encoding

Recent studies have shown the value of using deep learning models for mapping and characterizing how the brain represents and organizes information for natural vision. However, modeling the relationship between deep learning models and the brain (or encoding models), requires measuring cortical resp...