ConceptTNN / Tensor Neural Network
Tensor Neural Network
A network structure that represents a high-dimensional function as a sum of tensor products of one-dimensional functions. Its mathematical form is closely related to the canonical polyadic (CP) decomposition in tensor decomposition; high-dimensional integrals can be decomposed into products of one-dimensional integrals, avoiding high-dimensional gridding or Monte Carlo sampling.
Timeline (last 90 days)
Nov 6
APTNN introduces the canonical polynomial (CP) decomposition structure of tensor neural networks (TNN) into the approximate representation of the solution, and the equation residual retains the CP decomposition form under this representation.
Unverified50%