Zobrazeno 1 - 10
of 356
pro vyhledávání: '"Plis, Sergey"'
Neural networks, whice have had a profound effect on how researchers study complex phenomena, do so through a complex, nonlinear mathematical structure which can be difficult for human researchers to interpret. This obstacle can be especially salient
Externí odkaz:
http://arxiv.org/abs/2406.11825
Autor:
Ohib, Riyasat, Thapaliya, Bishal, Dziugaite, Gintare Karolina, Liu, Jingyu, Calhoun, Vince, Plis, Sergey
In this work, we propose Salient Sparse Federated Learning (SSFL), a streamlined approach for sparse federated learning with efficient communication. SSFL identifies a sparse subnetwork prior to training, leveraging parameter saliency scores computed
Externí odkaz:
http://arxiv.org/abs/2405.09037
Our understanding of learning dynamics of deep neural networks (DNNs) remains incomplete. Recent research has begun to uncover the mathematical principles underlying these networks, including the phenomenon of "Neural Collapse", where linear classifi
Externí odkaz:
http://arxiv.org/abs/2402.06751
Autor:
Mathur, Mrinal, Plis, Sergey
Deep learning models have become increasingly computationally intensive, requiring extensive computational resources and time for both training and inference. A significant contributing factor to this challenge is the uniform computational effort exp
Externí odkaz:
http://arxiv.org/abs/2312.12781
Performing volumetric image processing directly within the browser, particularly with medical data, presents unprecedented challenges compared to conventional backend tools. These challenges arise from limitations inherent in browser environments, su
Externí odkaz:
http://arxiv.org/abs/2310.16162
Deep learning (DL) models have been popular due to their ability to learn directly from the raw data in an end-to-end paradigm, alleviating the concern of a separate error-prone feature extraction phase. Recent DL-based neuroimaging studies have also
Externí odkaz:
http://arxiv.org/abs/2307.09615
Autor:
Geenjaar, Eloy, Kim, Donghyun, Ohib, Riyasat, Duda, Marlena, Kashyap, Amrit, Plis, Sergey, Calhoun, Vince
The neural dynamics underlying brain activity are critical to understanding cognitive processes and mental disorders. However, current voxel-based whole-brain dimensionality reduction techniques fall short of capturing these dynamics, producing laten
Externí odkaz:
http://arxiv.org/abs/2305.14369
Autor:
Ohib, Riyasat, Thapaliya, Bishal, Gaggenapalli, Pratyush, Liu, Jingyu, Calhoun, Vince, Plis, Sergey
Federated learning (FL) enables the training of a model leveraging decentralized data in client sites while preserving privacy by not collecting data. However, one of the significant challenges of FL is limited computation and low communication bandw
Externí odkaz:
http://arxiv.org/abs/2304.07488
Data scarcity is a notable problem, especially in the medical domain, due to patient data laws. Therefore, efficient Pre-Training techniques could help in combating this problem. In this paper, we demonstrate that a model trained on the time directio
Externí odkaz:
http://arxiv.org/abs/2211.16398
Autor:
Fedorov, Alex, Geenjaar, Eloy, Wu, Lei, Sylvain, Tristan, DeRamus, Thomas P., Luck, Margaux, Misiura, Maria, Hjelm, R Devon, Plis, Sergey M., Calhoun, Vince D.
Recent neuroimaging studies that focus on predicting brain disorders via modern machine learning approaches commonly include a single modality and rely on supervised over-parameterized models.However, a single modality provides only a limited view of
Externí odkaz:
http://arxiv.org/abs/2209.02876