Fast Code Detection in Sequential Data Using Neural Networks For Communication Applications

摘要

In recent years, fast neural networks for object/Face detection have been introduced based on cross correlation in frequency domain between the input image and the weights of neural networks. In a previous paper, it has been proved that for those fast neural networks to give correct results as conventional neural networks, either the weights of neural networks or the input image must be symmetric. In case of converting the input image into a symmetric one, those fast neural networks become slower than conventional neural networks. In another paper, a new form of symmetry for the input image to fast the operation of neural networks is presented. In this paper, the idea of converting the input data into symmetric form is applied to fast the detection of a certain code in a given sequential input data. Simulation results using Matlab confirm the theoretical computations.