Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
2
1
3
3
Findings suggest that optimal, high-capacity memory representations are not formed in flat minima, but are dynamically sculpted at the highly curved boundaries of geometric singularities.
A geometric analysis of the learning trajectories on the statistical manifold of a KLR-trained Hopfield network is provided, establishing that the highly structured geometry of the Ridge is optimally suited for information-geometric optimization.