SP2RINT trains physically realizable meta-optical neural networks by progressively projecting relaxed banded transfer matrices onto Maxwell-constrained metasurface designs through patched, parallel adjoint inverse design.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.optics 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SP2RINT: Spatially-Decoupled Physics-Inspired Progressive Inverse Optimization for Scalable, PDE-Constrained Meta-Optical Neural Network Training
SP2RINT trains physically realizable meta-optical neural networks by progressively projecting relaxed banded transfer matrices onto Maxwell-constrained metasurface designs through patched, parallel adjoint inverse design.