A hybrid MGA-MSGD ANN training approach for approximate solution of linear elliptic PDEs.
Hamidreza DehghaniAndreas ZilianPublished in: CoRR (2020)
Keyphrases
- partial differential equations
- artificial neural networks
- feed forward neural networks
- evolutionary artificial neural networks
- using artificial neural networks
- back propagation
- test set
- genetic algorithm
- operator splitting
- hybrid intelligent
- training phase
- image denoising
- training process
- training examples
- numerical methods
- multi layer perceptron
- numerical solution
- supervised learning
- recurrent neural networks
- anisotropic diffusion
- online learning
- training set
- spatial filters
- multiscale
- feedforward artificial neural networks
- data sets