### Abstract

This paper presents convergence analyses of the stochastic gradient adaptive algorithms based on the high order error power criteria. In particular, our attention has focused on investigating the statistical behaviors of the least mean absolute third (LMAT) and the least mean fourth (LMF) adaptive algorithms. For each algorithm, under a set of mild assumptions, we have derived nonlinear evolution equations that characterize the mean and mean-squared behavior of the algorithm. Computer simulation examples show fairly good agreements between the theoretical and actual behaviors of the two algorithms.

Original language | English |
---|---|

Pages | 109-112 |

Number of pages | 4 |

State | Published - 1996 Dec 1 |

Event | Proceedings of the 1996 IEEE Asia Pacific Conference on Circuits and Systems - Seoul, South Korea Duration: 1996 Nov 18 → 1996 Nov 21 |

### Other

Other | Proceedings of the 1996 IEEE Asia Pacific Conference on Circuits and Systems |
---|---|

City | Seoul, South Korea |

Period | 96/11/18 → 96/11/21 |

### Fingerprint

### Cite this

*Adaptive filters based on the high order error statistics*. 109-112. Paper presented at Proceedings of the 1996 IEEE Asia Pacific Conference on Circuits and Systems, Seoul, South Korea, .

}

**Adaptive filters based on the high order error statistics.** / Cho, Sung Ho; Kim, Sang Duck.

Research output: Contribution to conference › Paper

TY - CONF

T1 - Adaptive filters based on the high order error statistics

AU - Cho, Sung Ho

AU - Kim, Sang Duck

PY - 1996/12/1

Y1 - 1996/12/1

N2 - This paper presents convergence analyses of the stochastic gradient adaptive algorithms based on the high order error power criteria. In particular, our attention has focused on investigating the statistical behaviors of the least mean absolute third (LMAT) and the least mean fourth (LMF) adaptive algorithms. For each algorithm, under a set of mild assumptions, we have derived nonlinear evolution equations that characterize the mean and mean-squared behavior of the algorithm. Computer simulation examples show fairly good agreements between the theoretical and actual behaviors of the two algorithms.

AB - This paper presents convergence analyses of the stochastic gradient adaptive algorithms based on the high order error power criteria. In particular, our attention has focused on investigating the statistical behaviors of the least mean absolute third (LMAT) and the least mean fourth (LMF) adaptive algorithms. For each algorithm, under a set of mild assumptions, we have derived nonlinear evolution equations that characterize the mean and mean-squared behavior of the algorithm. Computer simulation examples show fairly good agreements between the theoretical and actual behaviors of the two algorithms.

UR - http://www.scopus.com/inward/record.url?scp=0030420592&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0030420592

SP - 109

EP - 112

ER -