Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/12034
Title: Extending the extreme physical information to universal cognitive models via a confident information first principle
Authors: Zhao, X
Hou, Y
Song, D
Li, W 
Keywords: Boltzmann machine
Fisher information
Information geometry
Parametric reduction
Issue Date: 2014
Publisher: MDPI AG
Source: Entropy, 2014, v. 16, no. 7, p. 3670-3688 How to cite?
Journal: Entropy 
Abstract: The principle of extreme physical information (EPI) can be used to derive many known laws and distributions in theoretical physics by extremizing the physical information loss K, i.e., the difference between the observed Fisher information I and the intrinsic information bound J of the physical phenomenon being measured. However, for complex cognitive systems of high dimensionality (e.g., human language processing and image recognition), the information bound J could be excessively larger than I (J ? I), due to insufficient observation, which would lead to serious over-fitting problems in the derivation of cognitive models. Moreover, there is a lack of an established exact invariance principle that gives rise to the bound information in universal cognitive systems. This limits the direct application of EPI. To narrow down the gap between I and J, in this paper, we propose a confident-information-first (CIF) principle to lower the information bound J by preserving confident parameters and ruling out unreliable or noisy parameters in the probability density function being measured. The confidence of each parameter can be assessed by its contribution to the expected Fisher information distance between the physical phenomenon and its observations. In addition, given a specific parametric representation, this contribution can often be directly assessed by the Fisher information, which establishes a connection with the inverse variance of any unbiased estimate for the parameter via the Cram?r-Rao bound. We then consider the dimensionality reduction in the parameter spaces of binary multivariate distributions. We show that the single-layer Boltzmann machine without hidden units (SBM) can be derived using the CIF principle. An illustrative experiment is conducted to show how the CIF principle improves the density estimation performance.
URI: http://hdl.handle.net/10397/12034
ISSN: 1099-4300
DOI: 10.3390/e16073670
Appears in Collections:Journal/Magazine Article

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

1
Last Week
0
Last month
0
Citations as of Aug 14, 2017

WEB OF SCIENCETM
Citations

1
Last Week
0
Last month
0
Citations as of Aug 22, 2017

Page view(s)

31
Last Week
3
Last month
Checked on Aug 20, 2017

Google ScholarTM

Check

Altmetric



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.