Diese Seite ist aus
Gründen der Barrierefreiheit optimiert für aktuelle
Browser. Sollten Sie einen älteren Browser verwenden, kann es
zu Einschränkungen der Darstellung und Benutzbarkeit der
Website kommen!
In statistical learning benchmarking is the methodology of
comparing learners or algorithms with respect to a certain
performance measure. The benchmarking process abstractly consists of
three levels: Setup, Execution and Analysis. In each level different
statistical and computational aspects play a role.
This website gives some insights about the computational
implementation -- a comprehensive list of all our work on this topic
can be found at
the
project site of the working group.
Use current development version of the benchmark package.
Interactive bench plot
The interactive bench plot is a prototype of a bench plot version
with interactive elements. The implementation is based on the R
packages iplots and icp; we have patched the CRAN
versions of iplots and its related
packages: iplots,
icp,
rJava.
beplot.icp.R is a first version; it is a
proof-of-concept and the idea is to release a stable version within
the first CRAN version of
the benchmark
package.
The uci621 benchmark experiment
The uci621 is a benchmark experiment we used in our article
Exploratory and Inferential analysis of benchmark experiments
to illustrate our methods. Here we show how to reproduce the results
for each section using the benchmark package version
0.01. The raw data and the corresponding Rnw files are available on
demand.
