On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,291 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “Hyperalignment”

Deep Hyperalignmentq-bio.NC

DHA is a scalable method for functional alignment of fMRI datasets.

problem Functional alignment of fMRI datasets with nonlinearity, high-dimensionality, and large number of subjects.

method Deep Hyperalignment (DHA) using parametric approach, rank-

m

Singular Value Decomposition (SVD), and stochastic gradient descent.

result DHA achieves superior performance compared to other state-of-the-art HA algorithms in multi-subject fMRI analysis.

fMRI functional alignment deep learning SVD stochastic gradient descent

2017-10-11abs ↗pdf ↗

Local Discriminant Hyperalignment for multi-subject fMRI data alignmentstat.ML

A new method LDHA improves fMRI data alignment for cognitive state validation.

problem Accurate functional alignment across different subjects for MVP analysis.

method LDHA incorporates LDA into CCA for supervised fMRI alignment.

result LDHA outperforms other HA methods in MVP analysis.

fMRI MVP Hyperalignment Local Discriminant Analysis Canonical Correlation Analysis

2016-11-25abs ↗pdf ↗

Supervised Hyperalignment for multi-subject fMRI data alignmentstat.ML

SHA improves fMRI alignment for cognitive state discovery.

problem Optimal functional alignment in MVP analysis for multi-subject fMRI data.

method Supervised Hyperalignment (SHA) method that maximizes correlation within same categories and minimizes between distinct categories.

result SHA achieves up to 19% better performance for multi-class problems.

fMRI MVP analysis functional alignment cognitive states supervised learning

2020-01-09abs ↗pdf ↗

Gradient Hyperalignment for multi-subject fMRI data alignmentcs.LG

Gradient-HA aligns fMRI data faster and more accurately.

problem Aligning fMRI data from multiple subjects efficiently and accurately.

method Gradient-HA uses ICA and SGA to solve alignment issues.

result Gradient-HA outperforms other methods in big data fMRI analysis.

fMRI alignment ICA SGA big data

2018-07-07abs ↗pdf ↗