Abstract | ||
---|---|---|
In this paper, a method is introduced how to process the Discrete Fourier Transform (DFT) by a single-layer neural network with a linear transfer function. By implementing the suggested solution into neuro- hardware, advantage can be taken of actual parallel processing of spectral components of different frequencies and of different coefficients of each spectral line. When computing the DFT due to input data pre-processing for a certain neural network solution, a stand alone solution of neural networks without the necessity of additional computational resources can be achieved. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1109/CIS.2008.36 | CIS (1) |
Keywords | Field | DocType |
single-layer neural network,actual parallel processing,neural networks,discrete fourier transform,different frequency,neural network,different coefficient,suggested solution,discrete fourier transform computation,spectral component,spectral line,certain neural network solution,time frequency analysis,parallel processing,transfer functions,artificial neural networks,dft,neural nets,transfer function | Computer science,Transfer function,Time–frequency analysis,Artificial intelligence,Discrete Fourier transform (general),Discrete Hartley transform,Discrete Fourier transform,Artificial neural network,Fractional Fourier transform,Machine learning,Computation | Conference |
Citations | PageRank | References |
1 | 0.43 | 0 |
Authors | ||
1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Rosemarie Velik | 1 | 45 | 5.87 |