Interpretable Conservation Law Estimation by Deriving the Symmetries of Dynamics from Trained Deep Neural Networks.
Yoh-ichi MototakePublished in: CoRR (2020)
Keyphrases
- neural network
- multilayer perceptron
- trained neural networks
- training process
- multi layer perceptron
- auto associative
- fuzzy logic
- pattern recognition
- dynamical systems
- artificial neural networks
- trained neural network
- estimation algorithm
- fuzzy systems
- back propagation
- multi layer
- recurrent neural networks
- robust estimation
- machine learning
- neural nets
- nonlinear dynamics
- neural network model
- backpropagation algorithm
- data sets
- feed forward neural networks
- rule extraction
- estimation process
- hidden units
- estimation accuracy
- accurate estimation
- hidden layer
- genetic algorithm
- feed forward
- classification rules
- self organizing maps
- fault diagnosis
- expert systems