Filters








72 Hits in 1.1 sec

Hyperalignment of Multi-subject fMRI Data by Synchronized Projections [chapter]

Raif M. Rustamov, Leonidas Guibas
2016 Lecture Notes in Computer Science  
Group analysis of fMRI data via multivariate pattern methods requires accurate alignments between neuronal activities of dierent subjects in order to attain competitive inter-subject classication rates  ...  While hyperalignment is very successful in terms of classication performance, its anatomy free nature excludes the use of potentially helpful information inherent in anatomy.  ...  Figure 1 1 shows the performance comparison of ve dierent approaches to alignment of multi-subject fMRI data.  ... 
doi:10.1007/978-3-319-45174-9_12 fatcat:6u4qn4cphvd55crz3jcjdwxnai

Local Discriminant Hyperalignment for multi-subject fMRI data alignment [article]

Muhammad Yousefnezhad, Daoqiang Zhang
2016 arXiv   pre-print
However, analyzing multi-subject fMRI data requires accurate functional alignments between neuronal activities of different subjects, which can rapidly increase the performance and robustness of the final  ...  Experimental studies on multi-subject MVP analysis confirm that the LDHA method achieves superior performance to other state-of-the-art HA algorithms.  ...  This work was supported in part by the National Natural Science Foundation of China (61422204 and 61473149), Jiangsu Natural Science Foundation for Distinguished Young Scholar (BK20130034) and NUAA Fundamental  ... 
arXiv:1611.08366v1 fatcat:44tvjzlhnnaglnlnhmatxbmfim

Local Discriminant Hyperalignment for multi-subject fMRI data alignment [article]

Muhammad Yousefnezhad, Daoqiang Zhang
2016 bioRxiv   pre-print
However, analyzing multi-subject fMRI data requires accurate functional alignments between neuronal activities of different subjects, which can rapidly increase the performance and robustness of the final  ...  Experimental studies on multi-subject MVP analysis confirm that the LDHA method achieves superior performance to other state-of-the-art HA algorithms.  ...  This work was supported in part by the National Natural Science Foundation of China (61422204 and 61473149), Jiangsu Natural Science Foundation for Distinguished Young Scholar (BK20130034) and NUAA Fundamental  ... 
doi:10.1101/092247 fatcat:iw3mfk2osbchdnjzqlsapnaqom

The neural basis of intelligence in fine-grained cortical topographies [article]

Ma Feilong, J. Swaroop Guntupalli, James V Haxby
2020 bioRxiv   pre-print
Using hyperalignment, we were able to model these fine-grained architectural differences by resolving idiosyncratic interindividual variation of fine-grained topographies of functional connectivity.  ...  Intelligent thought is the product of efficient neural information processing.  ...  Declarations of interests The authors declare no competing interests.  ... 
doi:10.1101/2020.06.06.138099 fatcat:v5rjez2hazazdmjtgocnelacre

Gradient Hyperalignment for multi-subject fMRI data alignment [article]

Tonglin Xu, Muhammad Yousefnezhad, Daoqiang Zhang
2018 arXiv   pre-print
This paper proposes Gradient Hyperalignment (Gradient-HA) as a gradient-based functional alignment method that is suitable for multi-subject fMRI datasets with large amounts of samples and voxels.  ...  Multi-subject fMRI data analysis is an interesting and challenging problem in human brain decoding studies.  ...  Conclusion This paper proposes a gradient-based functional alignment algorithm in order to apply hyperalignment to multi-subject fMRI big data.  ... 
arXiv:1807.02612v1 fatcat:di67gtcvzbbe3jbbqkphgcw2wu

Deep Hyperalignment [article]

Muhammad Yousefnezhad, Daoqiang Zhang
2017 arXiv   pre-print
This paper proposes Deep Hyperalignment (DHA) as a regularized, deep extension, scalable Hyperalignment (HA) method, which is well-suited for applying functional alignment to fMRI datasets with nonlinearity  ...  Experimental studies on multi-subject fMRI analysis confirm that the DHA method achieves superior performance to other state-of-the-art HA algorithms.  ...  Acknowledgments This work was supported in part by the National Natural Science Foundation of China (61422204, 61473149, and 61732006), and NUAA Fundamental Research Funds (NE2013105).  ... 
arXiv:1710.03923v1 fatcat:5wi2b42kjrhrtie4db366m2d6q

Supervised Hyperalignment for multi-subject fMRI data alignment

Muhammad Yousefnezhad, Alessandro Selvitella, Liangxiu Han, Daoqiang Zhang
2020 IEEE Transactions on Cognitive and Developmental Systems  
Hyperalignment has been widely employed in Multivariate Pattern (MVP) analysis to discover the cognitive states in the human brains based on multi-subject functional Magnetic Resonance Imaging (fMRI) datasets  ...  Experiments on multi-subject datasets demonstrate that SHA method achieves up to 19% better performance for multi-class problems over the state-of-the-art HA algorithms.  ...  However, neuronal activities in multi-subject fMRI dataset must be aligned to improve the performance of the final results [1] , [6] .  ... 
doi:10.1109/tcds.2020.2965981 fatcat:f2w35kom5bahjpfgnmwrsn6nkm

Graph-Based Decoding Model for Functional Alignment of Unaligned fMRI Data

Weida Li, Mingxia Liu, Fang Chen, Daoqiang Zhang
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
fMRI data.  ...  Aggregating multi-subject functional magnetic resonance imaging (fMRI) data is indispensable for generating valid and general inferences from patterns distributed across human brains.  ...  To tackle the singularity caused by the HSLT resolution of fMRI, Regularized Hyperalignment (RHA) was developed by Xu et al. (Xu et al. 2012) .  ... 
doi:10.1609/aaai.v34i03.5650 fatcat:jbw3yf4uvncq7piiqslsatv4xy

Community-driven methods development in naturalistic neuroscience [article]

Elizabeth DuPre
2020 Figshare  
I consider two case studies from my own work investigating methods for functional alignment (or hyperalignment) as well as multi-echo driven denoising of fMRI signals.  ...  Opportunities and challenges for community-driven neuroscience methods development in the era of "deep data" are discussed.  ...  General outline ○ Community-driven methods: what and why ○ Lessons from fmralign: constraints from data availability ○ Lessons from tedana: domain-specific software development Multi-echo fMRI ○ Provides  ... 
doi:10.6084/m9.figshare.12366944 fatcat:mjzapzyi3vcbxdezyct3wjxcau

fMRI-based Decoding of Visual Information from Human Brain Activity: A Brief Review

Shuo Huang, Wei Shao, Mei-Ling Wang, Dao-Qiang Zhang
2021 International Journal of Automation and Computing  
However, the unprecedented scale and complexity of the fMRI data have presented critical computational bottlenecks requiring new scientific analytic tools.  ...  Given the increasingly important role of machine learning in neuroscience, a great many machine learning algorithms are presented to analyze brain activities from the fMRI data.  ...  complexity of the valuable fMRI data.  ... 
doi:10.1007/s11633-020-1263-y fatcat:kwls2cvw4zgd5dti5d54uy6pgi

Hyperalignment: Modeling shared information encoded in idiosyncratic cortical topographies

James V Haxby, J Swaroop Guntupalli, Samuel A Nastase, Ma Feilong
2020 eLife  
In this Perspective, we present the conceptual framework that motivates hyperalignment, its computational underpinnings for joint modeling of a common information space and idiosyncratic cortical topographies  ...  Hyperalignment captures shared information by projecting pattern vectors for neural responses and connectivities into a common, high-dimensional information space, rather than by aligning topographies  ...  Higher bsMVPC than within-subject MVPC of hyperaligned data demonstrated the added power of using large multi-subject data sets for training a pattern classifier, which hyperalignment makes possible.  ... 
doi:10.7554/elife.56601 pmid:32484439 fatcat:dbikkgynz5fx3hpxyjdmal5bn4

Graph-Based Decoding Model for Functional Alignment of Unaligned fMRI Data [article]

Weida Li, Mingxia Liu, Fang Chen, Daoqiang Zhang
2019 arXiv   pre-print
fMRI data.  ...  Aggregating multi-subject functional magnetic resonance imaging (fMRI) data is indispensable for generating valid and general inferences from patterns distributed across human brains.  ...  Acknowledgments This work was in part supported by the National Natural Science Foundation of China (Nos. 61876082, 61732006, 61861130366, 61703301), the National Key R&D Program of China (Nos. 2018YFC2001600  ... 
arXiv:1905.05468v8 fatcat:4p2klqaojfeuzculchlbcynxyu

Multi-Objective Cognitive Model: a supervised approach for multi-subject fMRI analysis [article]

Muhammad Yousefnezhad, Daoqiang Zhang
2018 arXiv   pre-print
As a standard pipeline in the MVP analysis, brain patterns in multi-subject fMRI dataset must be mapped to a shared space and then a classification model is generated by employing the mapped patterns.  ...  Indeed, each step in the pipeline includes an objective function with independent optimization approach, where the best solution of each step may not be optimum for the next steps.  ...  Acknowledgements This work was supported in part by the National Natural Science Foundation of China (61422204 and 61473149) , and NUAA Fundamental Research Funds (NE2013105).  ... 
arXiv:1808.01642v1 fatcat:xszkav27nna23fxslso6lnwoou

Transferring and Generalizing Deep-Learning-based Neural Encoding Models across Subjects [article]

Haiguang Wen, Junxing Shi, Wei Chen, Zhongming Liu
2017 bioRxiv   pre-print
For the proof of principle, we applied these methods to functional magnetic resonance imaging (fMRI) data from three subjects watching tens of hours of naturalistic videos, while deep residual neural network  ...  However, modeling the relationship between deep learning models and the brain (or encoding models), requires measuring cortical responses to large and diverse sets of natural visual stimuli from single  ...  We expected that searchlight hyperalignment of multi-voxel responses could better co-register the cortical representational space between subjects (Guntupalli et al., 2016) to improve the efficacy of  ... 
doi:10.1101/171017 fatcat:ssjlqrrwhbbxlmn4ntuv6kzk74

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

Haiguang Wen, Junxing Shi, Wei Chen, Zhongming Liu
2018 NeuroImage  
For the proof of principle, we applied these methods to functional magnetic resonance imaging (fMRI) data from three subjects watching tens of hours of naturalistic videos, while deep residual neural network  ...  However, modeling the relationship between deep learning models and the brain (or encoding models), requires measuring cortical responses to large and diverse sets of natural visual stimuli from single  ...  We expected that searchlight hyperalignment of multi-voxel responses could better co-register the cortical representational space between subjects (Guntupalli et al., 2016) to improve the efficacy of  ... 
doi:10.1016/j.neuroimage.2018.04.053 pmid:29705690 pmcid:PMC5976558 fatcat:ws4xz36cfzepriujcbv4zrvlle
« Previous Showing results 1 — 15 out of 72 results