The Open UniversitySkip to content
 

Extending the extreme physical information to universal cognitive models via a confident information first principle

Zhao, Xiaozhao; Hou, Yuexian; Song, Dawei and Li, Wenjie (2014). Extending the extreme physical information to universal cognitive models via a confident information first principle. Entropy, 16(7) pp. 3670–3688.

URL: http://www.mdpi.com/1099-4300/16/7/3670
DOI (Digital Object Identifier) Link: https://doi.org/10.3390/e16073670
Google Scholar: Look up in Google Scholar

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 Cramér–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.

Item Type: Journal Item
Copyright Holders: 2017 The Authors; licensee MDPI, Basel, Switzerland
ISSN: 1099-4300
Academic Unit/School: Faculty of Science, Technology, Engineering and Mathematics (STEM) > Computing and Communications
Faculty of Science, Technology, Engineering and Mathematics (STEM)
Item ID: 40778
Depositing User: Dawei Song
Date Deposited: 03 Sep 2014 15:21
Last Modified: 29 Nov 2016 16:00
URI: http://oro.open.ac.uk/id/eprint/40778
Share this page:

Metrics

Altmetrics from Altmetric

Citations from Dimensions

Actions (login may be required)

Policies | Disclaimer

© The Open University   contact the OU