Statistic Complexity: Combining Kolmogorov Complexity with an Ensemble Approach
Frank Emmert-Streib · 2010
Read Statistic Complexity: Combining Kolmogorov Complexity with an Ensemble Approach by Frank Emmert-Streib (2010) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0012256.txt.
Description
Frank Emmert-Streib proposed a new measure of complexity in PLOS ONE in 2010. Judging how complex an observed object or pattern is has resisted a single good answer for decades. The classic approach, based on the shortest possible description, is elegant but often impossible to compute for real data, and it treats random noise as maximally complex, which clashes with intuition.
His measure, statistic complexity, joins that classic idea with an ensemble approach that samples many descriptions. It is designed to rate structured patterns as complex and both total order and total randomness as simpler. A workable complexity measure is useful anywhere patterns must be compared, from genomes to markets to machine learning.
Catalog record
| CREATOR | Frank Emmert-Streib |
|---|---|
| YEAR | 2010 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 27 KB |
| LICENSE | Creative Commons Attribution License |
| RIGHTS | CC BY |
| SOURCE | PLOS ONE |
Source: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0012256