cag-nasbench. Does CAG γ (Fiedler value of cell DAG's normalized Laplacian) predict ANN training convergence? Tested on NAS-Bench-201 across 15,625 pre-trained architectures without training.

github.com/tomdif/cag-nasbench

Vaya's read on this project

Problem, audience, market, and the verdict — sign in to see it.

Updates

No recent activity.