NeuRecover: Regression-Controlled Repair of Deep Neural Networks with Training History.
Shogo TokuiSusumu TokumotoAkihito YoshiiFuyuki IshikawaTakao NakagawaKazuki MunakataShinji KikuchiPublished in: SANER (2022)
Keyphrases
- neural network
- training process
- training algorithm
- feedforward neural networks
- multi layer perceptron
- feed forward neural networks
- artificial neural networks
- neural network training
- training patterns
- radial basis function network
- pattern recognition
- backpropagation algorithm
- back propagation
- multi layer
- training set
- error back propagation
- learning machines
- self organizing maps
- regression model
- deep architectures
- partial least squares
- recurrent networks
- fuzzy systems
- training examples
- model selection
- supervised learning
- regression problems
- linear regression
- recurrent neural networks
- feed forward
- regression method
- fault diagnosis
- regression function
- online learning
- neural network structure
- active learning
- decision trees