Group Method of Data Handling (GMDH) is a family of mathematical modeling and nonlinear regression algorithms, which is originally proposed by Alexey Grigorevich Ivakhnenko, an Ukrainian scientist and mathematician, in 1968. This approach is also known as Polynomial Neural Network and can be assumed as a specific type of supervised Artificial Neural Network (ANN). In addition to modeling specifications, GMDH uses the idea of Natural Selection to control the size, complexity and accuracy of network. The main application of GMDH is modeling of complex systems, function approximation, nonlinear regression, and pattern recognition.
For more information on GMDH, you can refer to related article in Wikipedia, available in this link. Also, you can find more detailed description of the GMDH algorithms, latest news, tutorials, and other resources about GMDH, in gmdh.net website.
In this post, we are going to share with you, the structured MATLAB implementation of GMDH, which can be used easily to perform modeling, function approximation and regression tasks. The framework developed in this project, can be easily modified to use with other supervised learning applications, such as Time-Series Prediction and Classification.
The download link of this project follows.
Implementation of Group Method of Data Handling (GMDH) in MATLABDownload
Citing This Work
If you wish, you can cite this content as follows.
Cite as:Mostapha Kalami Heris, Group Method of Data Handling (GMDH) in MATLAB (URL: https://yarpiz.com/263/ypml113-gmdh), Yarpiz, 2015.