Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems.
Logan G. WrightTatsuhiro OnoderaMartin M. SteinTianyu WangDarren T. SchachterZoey HuPeter L. McMahonPublished in: CoRR (2021)
Keyphrases
- physical systems
- backpropagation algorithm
- neural network
- back propagation
- multilayer feedforward
- multilayer perceptron
- feedforward neural networks
- feed forward neural networks
- activation function
- complex systems
- backpropagation learning algorithm
- hidden layer
- qualitative and quantitative
- artificial neural networks
- multi layer perceptron
- learning rate
- model based diagnosis
- qualitative models
- causal models
- training algorithm
- neural network model
- reasoning about physical systems
- pattern recognition
- neural nets
- feed forward
- dynamic programming
- learning algorithm
- multi layer
- bp neural network
- dynamic systems
- radial basis function
- linear combination
- computational intelligence
- search space