Neural realization of fast linear filters
International Symposium on VIPromCom Video/Image Processing and Multimedia Communications - Trang 153-157
Tóm tắt
The paper presents a neural network architecture for linear filtering of signals based on a scheme for fast calculation of orthogonal transformations. Compared to the known standard filtering schemes the network offers high training efficiency accompanied by substantial simplicity of realization. Additionally, the same basic network topology enables realization of diverse transformations.
Từ khóa
#Nonlinear filters #Neural networks #Filtering #Maximum likelihood detection #Neurons #Discrete Fourier transforms #Computer science #Computer architecture #Network topology #Image codingTài liệu tham khảo
10.1109/78.212760
10.1109/TASSP.1984.1164399
jacymirski, 2001, A Novel Method of Building Fast Fourier Transform Algorithms, Proceedings of the International Conference on Signals and Electronic Systems (ICSES'2001), 415
jacymirski, 2000, Fast Learning Neural Network for Linear Filtering of Signals, Proc 5th Conf Neural Netw Soft Comput, 130
yatsymirskyy, 1999, Lattice Structures for Fourier, Hartley, Cosine and Sine Transformations, Modelling and Information Technologies, 173
bracewell, 1986, The Hartley Transform
fa-long, 1998, Applied Neural Networks for Signal Processing