FFX: Fast, Scalable, Deterministic Symbolic Regression Technology

Created by W.Langdon from gp-bibliography.bib Revision:1.8051

@InCollection{McConaghy:2011:GPTP,

• author = "Trent McConaghy",
• title = "{FFX}: Fast, Scalable, Deterministic Symbolic Regression Technology",
• booktitle = "Genetic Programming Theory and Practice IX",
• year = "2011",
• editor = "Rick Riolo and Ekaterina Vladislavleva and Jason H. Moore",
• series = "Genetic and Evolutionary Computation",
• address = "Ann Arbor, USA",
• month = "12-14 " # may,
• publisher = "Springer",
• chapter = "13",
• pages = "235--260",
• keywords = "genetic algorithms, genetic programming, technology, symbolic regression, pathwise, regularisation, real-world problems, machine learning, lasso, ridge regression, elastic net, integrated circuits",
• isbn13 = "978-1-4614-1769-9",
• URL = "http://trent.st/content/2011-GPTP-FFX-paper.pdf",
• DOI = "doi:10.1007/978-1-4614-1770-5_13",
• slides_url = "http://www.trent.st/content/2011-GPTP-FFX-slides.pdf",
• size = "27 pages",
• abstract = "Symbolic regression is a common application for genetic programming (GP). we present a new non-evolutionary technique for symbolic regression that, compared to competent GP approaches on real-world problems, is orders of magnitude faster (taking just seconds), returns simpler models, has comparable or better prediction on unseen data, and converges reliably and deterministically. I dub the approach FFX, for Fast Function Extraction. FFX uses a recently developed machine learning technique, pathwise regularised learning, to rapidly prune a huge set of candidate basis functions down to compact models. FFX is verified on a broad set of real-world problems having 13 to 1468 input variables, out performing GP as well as several state-of-the-art regression techniques.",
• notes = "part of \cite{Riolo:2011:GPTP}",
• affiliation = "Solido Design Automation Inc., Saskatoon, Canada",

}

Genetic Programming entries for Trent McConaghy

Citations