Maps frozen MobileNetV2 features to Ising spins on quasi-cyclic LDPC graphs, operates a Random-Bond Ising Model at Nishimori temperature, and achieves 98.7% top-1 accuracy on ImageNet-10 and 84.92% on ImageNet-100 with 32-64 dimensional representations.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Attribute-based network partitioning with hydraulic and graph features stabilizes pipe roughness calibration, yielding repeatable results comparable to manual methods for key pipes.
citing papers explorer
-
Natural Image Classification via Quasi-Cyclic Graph Ensembles and Random-Bond Ising Models at the Nishimori Temperature
Maps frozen MobileNetV2 features to Ising spins on quasi-cyclic LDPC graphs, operates a Random-Bond Ising Model at Nishimori temperature, and achieves 98.7% top-1 accuracy on ImageNet-10 and 84.92% on ImageNet-100 with 32-64 dimensional representations.
-
The Elusive Nature of Roughness: Linking Hydraulics and Graph Theory for Water Distribution Networks Model Calibration
Attribute-based network partitioning with hydraulic and graph features stabilizes pipe roughness calibration, yielding repeatable results comparable to manual methods for key pipes.