Complex-valued B-spline neural network and its application to iterative frequency-domain decision feedback equalization for Hammerstein communication systems.
Sheng ChenXia HongEmad KhalafFuad E. AlsaadiChris J. HarrisPublished in: IJCNN (2016)
Keyphrases
- b spline
- communication systems
- complex valued
- decision feedback
- frequency domain
- orthogonal frequency division multiplexing
- activation function
- neural network
- recurrent neural networks
- basis functions
- spatial domain
- real valued
- multipath
- error propagation
- channel estimation
- computer systems
- low frequency
- hidden layer
- artificial neural networks
- back propagation
- feed forward
- radial basis function
- least squares
- affine transformation
- denoising
- linear equations
- subband
- multilayer perceptron
- wireless channels
- linear combination
- feature extraction
- recursive least squares
- filter bank
- bit error rate