- author = "Stuart W. Card",
- title = "Information distance based fitness and diversity metrics",
- booktitle = "GECCO 2010 Entropy, information and complexity",
- year = "2010",
- editor = "Stuart William Card and Yossi Borenstein",
- isbn13 = "978-1-4503-0073-5",
- keywords = "genetic algorithms, genetic programming, Measurement, Theory, evolutionary computation, machin e learning, fitness, diversity, metric, distance, mutual information, interaction information, algorithmic information, complexity, entropy, Kolmogorov Complexity, Kolmogorov Distance, Shannon Distance, Rajski Distance, Normalized Compression Distance, NCD, Multi-Objective Selection",
- pages = "1851--1854",
- month = "7-11 " # jul,
- organisation = "SIGEVO",
- address = "Portland, Oregon, USA",
-
DOI = "
doi:10.1145/1830761.1830815",
- publisher = "ACM",
- publisher_address = "New York, NY, USA",
- abstract = "Commensurate indicators of diversity and fitness with desirable metric properties are derived from information distances based on Shannon entropy and Kolmogorov complexity. These metrics measure various useful distances: from an information theoretic characterisation of the phenotypic behaviour of a candidate model in the population to that of an ideal model of the target system's input-output relationship (fitness); from behavior of one candidate model to that of another (total information diversity); from the information about the target provided by one model to that provided by another (target relevant information diversity); from the code of one model to that of another (genotypic representation diversity); etc. Algorithms are cited for calculating the Shannon entropy based metrics from discrete data and estimating analogs thereof from heuristically binned continuous data; references are cited to methods for estimating the Kolmogorov complexity based metric. Not in the paper, but at the workshop, results will be shown of applying these algorithms to several synthetic and real world data sets: the simplest known deterministic chaotic flow; symbolic regression test functions; industrial process monitoring and control variables; and international political leadership data. Ongoing work is outlined.",
-
notes = "Also known as \cite{1830815} Distributed on CD-ROM at
GECCO-2010.
ACM Order Number 910102.",
