Skip to content
arXiv cs.CV · Papers

Kohn-Sham Spectral Embedding on Sparse Graphs at the Nishimori Temperature for Image Classification

arXiv:2607.28428v2 Announce Type: replace-cross Abstract: We propose Kohn-Sham Spectral Embedding (KSSE), an energy-based model replacing the dense classifier of convolutional neural networks with a sparse-graph spectral embedding evaluated at the Nishimori temperature of an associated Random-Bond Ising Model (RBIM). M