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
Journal ArticleDOI
Heritability of individualized cortical network topography.
Kevin M. Anderson,Tian Ge,Tian Ge,Ru Kong,Lauren M. Patrick,R. Nathan Spreng,R. Nathan Spreng,Mert R. Sabuncu,Mert R. Sabuncu,B.T. Thomas Yeo,Avram J. Holmes,Avram J. Holmes +11 more
TL;DR: In this article, a nonlinear multidimensional estimation of heritability was used to demonstrate that individual variability in the size and topographic organization of cortical networks are under genetic control.
Proceedings Article
Self-Distillation as Instance-Specific Label Smoothing
Zhilu Zhang,Mert R. Sabuncu +1 more
TL;DR: In this article, an instance-specific label smoothing technique was proposed to promote predictive diversity without the need for a separately trained teacher model. And they provided an empirical evaluation of the proposed method.
Journal ArticleDOI
Fidelity imposed network edit (FINE) for solving ill-posed image reconstruction
Jinwei Zhang,Zhe Liu,Shun Zhang,Hang Zhang,Pascal Spincemaille,Thanh D. Nguyen,Mert R. Sabuncu,Yi Wang +7 more
TL;DR: Fidelity imposed network edit (FINE) is introduced, which modifies the weights of a pre-trained reconstruction network for each case in the testing dataset by minimizing an unsupervised fidelity loss function that is based on the forward physical model.
Journal ArticleDOI
Heritability and interindividual variability of regional structure-function coupling.
TL;DR: In this article, the authors quantify regional structural and functional coupling in healthy young adults using diffusion-weighted MRI and resting-state functional MRI data from the Human Connectome Project and study how SC-FC coupling may be heritable and varies between individuals.
Journal ArticleDOI
Machine Learning Methods Predict Individual Upper-Limb Motor Impairment Following Therapy in Chronic Stroke:
Ceren Tozlu,Dylan J. Edwards,Aaron D. Boes,Douglas Labar,K. Zoe Tsagaris,Joshua Silverstein,Heather Pepper Lane,Mert R. Sabuncu,Charles Liu,Amy Kuceyeski +9 more
TL;DR: Machine learning methods may enable clinicians to accurately predict a chronic stroke patient’s postintervention UE-FMA and the difference in motor threshold (MT) between the affected and unaffected hemispheres were the strongest predictors.