Multiresolution learning paradigm and signal prediction
Yao Liang, Edward W. Page · IEEE Transactions on Signal Processing · 1997
Current neural network learning processes, regardless of the learning algorithm and preprocessing used, are sometimes inadequate for difficult problems. We present a new learning concept and paradigm for neural networks, called multiresolution learning, based on multiresolution analysis in wavelet theory. The multiresolution learning paradigm can significantly improve the generalization performance of neural networks.