Adaptive Blending Units: Trainable Activation Functions for Deep Neural Networks.
Leon René SütfeldFlemming BriegerHolger FingerSonja FüllhaseGordon PipaPublished in: SAI (3) (2020)
Keyphrases
- activation function
- neural network
- hidden units
- feed forward
- neural nets
- hidden layer
- back propagation
- feed forward neural networks
- artificial neural networks
- hidden neurons
- neural architecture
- connection weights
- multilayer perceptron
- learning rate
- complex valued
- network architecture
- radial basis function
- fuzzy neural network
- feedforward neural networks
- basis functions
- hidden nodes
- pattern recognition
- global exponential stability
- multi layer perceptron
- artificial intelligence
- fuzzy logic
- multi layer
- neural network model
- training examples
- evolutionary algorithm
- expert systems
- learning algorithm