Search papers, labs, and topics across Lattice.
Kempner Institute for the Study of Natural and Artificial Intelligence at Harvard University
2
0
4
1
Conditioning on activity can boost DFA performance by nearly 40 percentage points, revealing critical insights into the geometry of weight updates in neural networks.
Adversarial training can effectively disentangle session-specific noise from task-relevant speech features in brain-computer interfaces, leading to more robust decoding across recording sessions.
