Extending Neural Network Verification to a Larger Family of Piece-wise Linear Activation Functions.
László AntalHana MasaraErika ÁbrahámPublished in: CoRR (2023)
Keyphrases
- activation function
- neural network
- piece wise linear
- back propagation
- artificial neural networks
- hidden layer
- neural nets
- feed forward neural networks
- feed forward
- hidden neurons
- connection weights
- neural architecture
- network architecture
- learning rate
- multilayer perceptron
- radial basis function
- feedforward neural networks
- sigmoid function
- multi layer perceptron
- neural network model
- basis functions
- fuzzy neural network
- training phase
- genetic algorithm
- fault diagnosis
- hidden nodes
- small number
- fuzzy logic
- pattern recognition