Deep Hyperalignment
This addresses the challenge of aligning fMRI data across subjects for neuroscience research, but it appears incremental as an extension of existing Hyperalignment methods.
The paper tackles the problem of functional alignment for fMRI datasets with nonlinearity, high-dimensionality, and many subjects by proposing Deep Hyperalignment (DHA), which achieves superior performance compared to other state-of-the-art Hyperalignment algorithms in experimental studies.
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, high-dimensionality (broad ROI), and a large number of subjects. Unlink previous methods, DHA is not limited by a restricted fixed kernel function. Further, it uses a parametric approach, rank-$m$ Singular Value Decomposition (SVD), and stochastic gradient descent for optimization. Therefore, DHA has a suitable time complexity for large datasets, and DHA does not require the training data when it computes the functional alignment for a new subject. Experimental studies on multi-subject fMRI analysis confirm that the DHA method achieves superior performance to other state-of-the-art HA algorithms.