M
Mert R. Sabuncu
Researcher at Cornell University
Publications - 148
Citations - 12746
Mert R. Sabuncu is an academic researcher from Cornell University. The author has contributed to research in topics: Computer science & Convolutional neural network. The author has an hindex of 24, co-authored 118 publications receiving 9297 citations. Previous affiliations of Mert R. Sabuncu include Massachusetts Institute of Technology & Harvard University.
Papers
More filters
Modulating human brain responses via optimal natural image selection and synthetic image generation
TL;DR: In this paper , the authors investigated the brain's regional activation selectivity and inter-individual differences in human brain responses to various sets of natural and synthetic (generated) images via two functional MRI (fMRI) studies and found that individual-specific synthetic (and not natural) images derived using a personalized encoding model elicited significantly higher responses compared to synthetic images derived from the group level or other subjects' encoding models.
Book ChapterDOI
Detecting Cannabis-Associated Cognitive Impairment Using Resting-State fNIRS
TL;DR: This work considers the novel problem of detecting cannabis intoxication based on resting-state fNIRS data and suggests that a recurrent neural network model trained on dynamic functional connectivity matrices, computed on sliding windows, coupled with the proposed data augmentation strategy yields the best accuracy for this application.
Journal ArticleDOI
Patchwork Learning: A Paradigm Towards Integrative Analysis across Diverse Biomedical Data Sources
TL;DR: In this paper , the authors introduce patchwork learning (PL), a novel paradigm that integrates information from disparate datasets composed of different data modalities (e.g., clinical free-text, medical images, omics) and distributed across separate and secure sites.
Journal ArticleDOI
A Simple Nadaraya-Watson Head can offer Explainable and Calibrated Classification
TL;DR: In this paper , the authors propose a non-learnable and nonparametric Nadaraya-Watson (NW) prediction head that can be used with any neural network architecture, where the weights are computed from distances between the query feature and support features.
Posted ContentDOI
Predicting response to motor therapy in chronic stroke patients using Machine Learning
Ceren Tozlu,Dylan J. Edwards,Aaron D. Boes,Douglas Labar,K. Zoe Tsagaris,Joshua Silverstein,Heather Pepper Lane,Mert R. Sabuncu,Charles Y. Liu,Amy Kuceyeski +9 more
TL;DR: The approach implemented here may enable clinicians to more accurately predict a chronic stroke patient’s individual response to intervention and improve the accuracy of prognosis in chronic stroke patients.