Scribd
Upload
154 views2 pages

Gptips: Genetic Programming & Symbolic Regression Toolbox For MATLAB

This document introduces GPTIPS, a genetic programming and symbolic regression toolbox for MATLAB. GPTIPS uses simulated evolution to automatically create accurate nonlinear equations to model and predict complex systems from input data without assuming a model structure. It can identify key predictive variables and build model portfolios of different complexity levels.

Uploaded by

moeinsarvaghad
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
154 views2 pages

Gptips: Genetic Programming & Symbolic Regression Toolbox For MATLAB

This document introduces GPTIPS, a genetic programming and symbolic regression toolbox for MATLAB. GPTIPS uses simulated evolution to automatically create accurate nonlinear equations to model and predict complex systems from input data without assuming a model structure. It can identify key predictive variables and build model portfolios of different complexity levels.

Uploaded by

moeinsarvaghad
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

8/5/13

GPTIPS

GPTIPS

Search this site

Home
FAQ
Features

GPTIPS

Downloads
News
Contact
Bugs
Application Areas

Genetic Programming & Symbolic Regression Toolbox for MATLAB

Dominic Searson
Newcastle University
UK

Download GPTIPS
Coming Soon: GPTIPS 2

What is GPTIPS?
GPTIPS is a free genetic programming (GP) and predictive modelling toolbox for MATLAB. It enables you
to:

Discover hidden, non-linear relationships in your data.

Use simulated evolution to automatically create compact and accurate non-linear equations to
predict the behaviour of physical systems.

Identify key predictive variables even when your data is noisy and highly correlated and there are a
large number of superfluous input variables.

Build models when you don't know the "true" underlying model structure.
Automatically generate a model portfolio containing models of different levels of complexity and
predictive quality.

GPTIPS is particularly effective at automatically generating symbolic non-linear regression models of


predictor response (input/output) data.
GPTIPS implements multigene genetic programming (MGGP) which combines the flexibility - and ability
to capture non-linear behaviour - of GP with the power of classical linear least squares parameter
estimation. However, you can choose to use "regular" single gene GP if you wish.
GPTIPS is completely open source, is written in standard MATLAB & has a pluggable architecture - it is
easy to write new functions to solve your own problems.
GPTIPS is aimed at scientists, engineers and students - you do not have to be an expert in evolutionary
computation or machine learning to use GPTIPS effectively.

Why use GPTIPS?


No a priori assumptions of model structure
https://sites.google.com/site/gptips4matlab/

1/2

8/5/13

GPTIPS

GPTIPS automatically evolves both the structure and the parameters of the mathematical model using the
supplied input variables and simple mathematical "building blocks".
Transparent compact portable models - what you see is what you get
GPTIPS models are simple mathematical equations. They can be easily and rapidly implemented in any
modern computing language by a non-modelling expert.
Automatic variable selection
GPTIPS automatically selects the input variables ("features") that best predict the output variable of
interest. GPTIPS can easily be used - as a variable selection method in its own right - to select variables
or non-linear combinations of variables as inputs for any other modelling method. GPTIPS has been
shown to be effective at variable selection even when there are > 1000 irrelevant input variables.
Testimonials:
"A remarkable control can be exerted over the maximum complexity of the model evolved by
MGGP in comparison with the standard GP."1
"Numerical examples show the superb accuracy, efficiency, and great potential of MGGP.
Contrary to artificial neural networks and many other soft computing tools, MGGP
provides constitutive prediction equations."1
"It can be observed (...) that the MGGP-based solution remarkably outperforms the other
models. In addition to its high performance, the MGGP-based equation is very simple, and
therefore, it can easily be manipulated in practical circumstances."1
"

MGGP has an advantage that once the evolved models are trained, they can be used as
quick and accurate tools for prediction purposes."1

1 Gandomi, AH & Alavi, AH, A new multi-gene genetic programming approach to non-linear system modeling. Part II:
geotechnical and earthquake engineering problems, Neural Comput & Applic, Springer, 2011, DOI 10.1007/s00521-011-0735y

Updated: 21st March 2013

Dominic Searson 2013

Subpages (2): Application Areas Features


Sign in | Report Abuse | Print Page | Remove Access | Powered By Google Sites

https://sites.google.com/site/gptips4matlab/

2/2

You might also like