Beyond Moments: Extending the Maximum Entropy Principle to Feature Distribution Constraints

被引：7

作者：

Baggenstoss, Paul M. ^{[1
]}

机构：

[1] Fraunhofer FKIE, D-53343 Wachtberg, Germany

来源：

ENTROPY | 2018年 / 20卷 / 09期

关键词：

maximum entropy principle; PDF projection; statistical inference; CLASSIFICATION;

D O I：

10.3390/e20090650

中图分类号：

O4 [物理学];

学科分类号：

0702 ;

摘要：

The maximum entropy principle introduced by Jaynes proposes that a data distribution should maximize the entropy subject to constraints imposed by the available knowledge. Jaynes provided a solution for the case when constraints were imposed on the expected value of a set of scalar functions of the data. These expected values are typically moments of the distribution. This paper describes how the method of maximum entropy PDF projection can be used to generalize the maximum entropy principle to constraints on the joint distribution of this set of functions.

引用

页数：13

共 22 条

[1]

[Anonymous], P EUSIPCO 2017 KOS G

[2]

[Anonymous], 11262 NUWC

[3]

[Anonymous], ENTROPY SPECIAL ISSU

[4]

[Anonymous], 11345 NUWC

[5]

[Anonymous], P EUR SIGN PROC C EU

[6]

[Anonymous], P 2015 23 EUR SIGN P

[7]

Bagenstoss PM, 1999, IEEE T SIGNAL PROCES, V47, P3428, DOI 10.1109/78.806092

[8] On the Duality Between Belief Networks and Feed-Forward Neural Networks [J].

Baggenstoss, Paul M. .

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2019, 30 (01) :190-200

[9] Maximum Entropy PDF Projection: A Review [J].

Baggenstoss, Paul M. .

BAYESIAN INFERENCE AND MAXIMUM ENTROPY METHODS IN SCIENCE AND ENGINEERING (MAXENT 2016), 2017, 1853

[10] Uniform Manifold Sampling (UMS): Sampling the Maximum Entropy PDF [J].

Baggenstoss, Paul M. .

IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2017, 65 (09) :2455-2470

← 1 2 3 →