Title :
Multidimensional wavelet frames
Author :
Kugarajah, Tharmarajah ; Zhang, Qinghua
Author_Institution :
Inst. for Syst. Res., Maryland Univ., College Park, MD, USA
fDate :
11/1/1995 12:00:00 AM
Abstract :
Pati and Krishnaprasad (1990) first studied the connection between neural networks and wavelet transforms. Zhang and Benveniste (1992) gave a different treatment of this connection. However, the problem of constructing multidimensional wavelet frames for use in neural networks has not been satisfactorily studied. In this paper, one-dimensional wavelet frame is generalized to the multidimensional case by using single-scaling and multiscaling parameters. The construction of multidimensional wavelet frames is also discussed. These results provide more insight on the use of wavelets in neural networks
Keywords :
neural nets; wavelet transforms; multidimensional wavelet frames; multiscaling parameter; neural networks; single-scaling parameter; wavelet transform; Costs; Error correction; Multidimensional signal processing; Multidimensional systems; Neural networks; Numerical analysis; Sufficient conditions; Tensile stress; Wavelet analysis; Wavelet transforms;
Journal_Title :
Neural Networks, IEEE Transactions on
