Decision feedback equalizers based on two weighted neural network

In this work, we present new decision-feedback equalizers based on two weighted neural networks. It is shown that the choice of an innovative cost functional based on the discriminative learning (DL) technique, coupled with a fast training paradigm, can provide neural equalizers that outperform stan...

Full description

Saved in:
Bibliographic Details
Main Authors: Hong Peng, Wen-Ming Cao, Pei-Liang Qiu
Format: Conference Proceeding
Language:English
Subjects:
Computer architecture
Decision feedback equalizers
Detectors
Interference
Modems
Neural networks
Neurofeedback
Neurons
Signal to noise ratio
Viterbi algorithm
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this work, we present new decision-feedback equalizers based on two weighted neural networks. It is shown that the choice of an innovative cost functional based on the discriminative learning (DL) technique, coupled with a fast training paradigm, can provide neural equalizers that outperform standard decision feedback equalizers (decision feedback Es) at a practical signal to the noise ratio (SNR). In particular, the novel neural sequence detector (NSD) is introduced, which allows extending of the concepts of Viterbi-like sequence estimation to neural architectures. Resulted architectures are competitive with the Viterbi solution from cost-performance aspects, as demonstrated in experimental tests.
DOI:10.1109/ICMLC.2004.1378576