Title :
Multiresolution learning paradigm and signal prediction
Author :
Liang, Yao ; Page, Edward W.
Author_Institution :
Dept. of Comput. Sci., Clemson Univ., SC, USA
fDate :
11/1/1997 12:00:00 AM
Abstract :
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
Keywords :
learning (artificial intelligence); neural nets; prediction theory; signal representation; signal resolution; sunspots; telecommunication traffic; time series; wavelet transforms; generalization performance; high-speed network traffic prediction; learning algorithm; multiresolution analysis; multiresolution learning paradigm; neural network learning; preprocessing; signal prediction; sunspot series; time series forecasting; wavelet representation; wavelet theory; AWGN; Adaptive equalizers; Biological neural networks; Digital communication; Digital magnetic recording; Intersymbol interference; Recurrent neural networks; Signal processing; Signal processing algorithms; Signal resolution;
Journal_Title :
Signal Processing, IEEE Transactions on
