A new stability condition for discrete time recurrent neural networks with complex-valued linear threshold neurons.
Wei ZhouJacek M. ZuradaPublished in: IJCNN (2014)
Keyphrases
- recurrent neural networks
- complex valued
- linear threshold
- hidden layer
- neural network
- activation function
- feed forward
- sampling algorithm
- boolean functions
- sufficient conditions
- learning algorithm
- markov chain
- artificial neural networks
- perceptron algorithm
- sample complexity
- fuzzy logic
- back propagation
- neural network model
- machine learning algorithms
- fuzzy neural network
- supervised learning