Adaptive receivers for removing linear and nonlinear intersymbol interference by mean of time delay neural nets (AR-TDNN)

摘要

A review is presented of several classical equalizers for data transmission, showing that they are special cases of a general time-delay neural net (TDNN). It is shown that the solution to the deconvolution problem for many transmission channel types, including linear and nonlinear distortions, can be solved by means of TDNN. Alternatively, TDNN can be seen as a generalization of currently used equalizers and as tools for discovering new ones.