Search papers, labs, and topics across Lattice.
Yneuro, University of California San Diego
3
0
4
EEG decoding performance scales predictably with data, but the optimal balance between subject diversity and scan time depends heavily on the model and dataset.
Subject-specific encoders can enhance EEG decoding by increasing class distinctiveness and effectively internalizing alignment without relying on traditional methods like Euclidean Alignment.
SPD Learn streamlines geometric deep learning with SPD matrices by providing a unified Python package that ensures manifold constraints via trivialization, enabling standard backpropagation for neural decoding.
