### Abstract

We present the general formulation for adaptive equalization by distribution learning in which conditional probability mass function (pmf) of the transmitted signal given the received is parametrized by a general neural network structure. The parameters of the pmf are computed by minimization of the accumulated relative entropy (ARE) cost function. The equivalence of ARE minimization to maximum partial log-likelihood (MPLL) estimation is established under certain regularity conditions which enables us to bypass the requirement that the true conditionals be known. The large sample properties of MPLL estimator are obtained under further regularity conditions, and the binary case with sigmoidal perceptron as the conditional pmf model is shown to be a special case of the new framework. Results are presented which show that the multilayer perceptron (MLP) equalizer based on ARE minimization can always recover from convergence at the wrong extreme whereas the mean square error (MSE) based MLP can not.

Original language | English (US) |
---|---|

Title of host publication | Neural Networks for Signal Processing - Proceedings of the IEEE Workshop |

Publisher | IEEE |

Pages | 541-550 |

Number of pages | 10 |

State | Published - 1995 |

Externally published | Yes |

Event | Proceedings of the 5th IEEE Workshop on Neural Networks for Signal Processing (NNSP'95) - Cambridge, MA, USA Duration: Aug 31 1995 → Sep 2 1995 |

### Other

Other | Proceedings of the 5th IEEE Workshop on Neural Networks for Signal Processing (NNSP'95) |
---|---|

City | Cambridge, MA, USA |

Period | 8/31/95 → 9/2/95 |

### Fingerprint

### ASJC Scopus subject areas

- Signal Processing
- Software
- Electrical and Electronic Engineering

### Cite this

*Neural Networks for Signal Processing - Proceedings of the IEEE Workshop*(pp. 541-550). IEEE.

**Maximum partial likelihood framework for channel equalization by distribution learning.** / Adali, Tulay; Liu, Xiao; Li, Ning; Sonmez, Mustafa (Kemal).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

*Neural Networks for Signal Processing - Proceedings of the IEEE Workshop.*IEEE, pp. 541-550, Proceedings of the 5th IEEE Workshop on Neural Networks for Signal Processing (NNSP'95), Cambridge, MA, USA, 8/31/95.

}

TY - GEN

T1 - Maximum partial likelihood framework for channel equalization by distribution learning

AU - Adali, Tulay

AU - Liu, Xiao

AU - Li, Ning

AU - Sonmez, Mustafa (Kemal)

PY - 1995

Y1 - 1995

N2 - We present the general formulation for adaptive equalization by distribution learning in which conditional probability mass function (pmf) of the transmitted signal given the received is parametrized by a general neural network structure. The parameters of the pmf are computed by minimization of the accumulated relative entropy (ARE) cost function. The equivalence of ARE minimization to maximum partial log-likelihood (MPLL) estimation is established under certain regularity conditions which enables us to bypass the requirement that the true conditionals be known. The large sample properties of MPLL estimator are obtained under further regularity conditions, and the binary case with sigmoidal perceptron as the conditional pmf model is shown to be a special case of the new framework. Results are presented which show that the multilayer perceptron (MLP) equalizer based on ARE minimization can always recover from convergence at the wrong extreme whereas the mean square error (MSE) based MLP can not.

AB - We present the general formulation for adaptive equalization by distribution learning in which conditional probability mass function (pmf) of the transmitted signal given the received is parametrized by a general neural network structure. The parameters of the pmf are computed by minimization of the accumulated relative entropy (ARE) cost function. The equivalence of ARE minimization to maximum partial log-likelihood (MPLL) estimation is established under certain regularity conditions which enables us to bypass the requirement that the true conditionals be known. The large sample properties of MPLL estimator are obtained under further regularity conditions, and the binary case with sigmoidal perceptron as the conditional pmf model is shown to be a special case of the new framework. Results are presented which show that the multilayer perceptron (MLP) equalizer based on ARE minimization can always recover from convergence at the wrong extreme whereas the mean square error (MSE) based MLP can not.

UR - http://www.scopus.com/inward/record.url?scp=0029239287&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029239287&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0029239287

SP - 541

EP - 550

BT - Neural Networks for Signal Processing - Proceedings of the IEEE Workshop

PB - IEEE

ER -