A linear three-layer neural network with constrained weights provably recovers the edge conductivities of a resistor network from boundary voltage-current data, with the conductivity stored in the second-layer weights.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.NA 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The discrete inverse conductivity problem solved by the weights of an interpretable neural network
A linear three-layer neural network with constrained weights provably recovers the edge conductivities of a resistor network from boundary voltage-current data, with the conductivity stored in the second-layer weights.