Decentralized distribution-sampled classification models with application to brain imaging

• Published in: Journal of neuroscience methods Vol. 329; p. 108418
• Main Authors: Lewis, Noah, Gazula, Harshvardhan, Plis, Sergey M., Calhoun, Vince D.
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.01.2020
• Subjects: Adult; Brain - diagnostic imaging; Datasets as Topic; Decentralized learning; Deep Learning; Female; Humans; Magnetic Resonance Imaging - methods; Magnetic Resonance Imaging - standards; Male; Models, Statistical; Models, Theoretical; Neuroimaging; Neuroimaging - methods; Neuroimaging - standards; Schizophrenia - diagnostic imaging; Statistical inference; Support Vector Machine; Deep learning; Neuroimaging; Decentralized learning; Statistical inference

•A novel yet simple approach to decentralized classification.•Reduces total network load compared to current multishot algorithms.•Maintains a prediction accuracy comparable to the centralized approach. In this age of big data, certain models require very large data stores in order to be informative...