Differentiable Programming Tensor Networks
Sign Up to like & getrecommendations! Published in 2019 at "Physical Review X"
DOI: 10.1103/physrevx.9.031041
Abstract: Differentiable programming is a fresh programming paradigm which composes parameterized algorithmic components and trains them using automatic differentiation (AD). The concept emerges from deep learning but is not only limited to training neural networks. We… read more here.
Keywords: programming tensor; tensor; differentiable programming; tensor network ... See more keywords
A Theory-guided Deep Neural Network for Time Domain Electromagnetic Simulation and Inversion Using a Differentiable Programming Platform
Sign Up to like & getrecommendations! Published in 2021 at "IEEE Transactions on Antennas and Propagation"
DOI: 10.1109/tap.2021.3098585
Abstract: In this communication, a trainable theory-guided recurrent neural network (RNN) equivalent to the finite-difference-time-domain (FDTD) method is exploited to formulate electromagnetic propagation, solve Maxwell’s equations and the inverse problem on differentiable programming platform Pytorch. For… read more here.
Keywords: neural network; programming platform; differentiable programming; theory guided ... See more keywords