- author = "Nicholas Freitag McPhee and Mitchell D. Finzel and Maggie M. Casale and Thomas Helmuth and Lee Spector",
- title = "A detailed analysis of a {PushGP} run",
- booktitle = "Genetic Programming Theory and Practice XIV",
- year = "2016",
- editor = "Rick Riolo and Bill Worzel and Brian Goldman and Bill Tozier",
- pages = "65--83",
- address = "Ann Arbor, USA",
- month = "19-21 " # may,
- publisher = "Springer",
- keywords = "genetic algorithms, genetic programming, PushGP, ancestry graph, lineage, inheritance",
- isbn13 = "978-3-319-97087-5",
-
URL = "
https://www.springer.com/us/book/9783319970875",
-
DOI = "
doi:10.1007/978-3-319-97088-2_5",
-
abstract = "In evolutionary computation runs there is a great deal
of data that could be saved and analysed. This data is
often put aside, however, in favour of focusing on the
final outcomes, typically captured and presented in the
form of summary statistics and performance plots. Here
we examine a genetic programming run in detail and
trace back from the solution to determine how it was
derived. To visualize this genetic programming run, the
ancestry graph is extracted, running from the
solution(s) in the final generation up to their
ancestors in the initial random population.
The key instructions in the solution are also identified, and a genetic ancestry graph is constructed, a subgraph of the ancestry graph containing only those individuals contributed genetic information (or instructions) to the solution. This visualization and our ability to trace these key instructions throughout the run allowed us to identify general inheritance patterns and key evolutionary moments in this run.",
-
notes = "
Part of \cite{Tozier:2016:GPTP} published after the workshop",
