The Neural Network shifted-Proper Orthogonal Decomposition: a Machine Learning Approach for Non-linear Reduction of Hyperbolic Equations.
Davide PapapiccoNicola DemoMichele GirfoglioGiovanni StabileGianluigi RozzaPublished in: CoRR (2021)
Keyphrases
- neural network
- conservation laws
- highly non linear
- back propagation
- pattern recognition
- artificial neural networks
- neural network model
- neural network is trained
- genetic algorithm
- learning vector quantization
- differential equations
- neural nets
- reduction method
- partial differential equations
- mathematical model
- activation function
- numerical solution
- bp neural network
- synaptic weights
- network model
- training process
- hidden layer
- fuzzy neural network
- linear equations
- decomposition methods
- feed forward