A software tool for complex-valued neural network: CV-ANN

Complex valued artificial neural networks (CVANN); is a kind of artificial neural network of which parameters such as weight, threshold, input and output consisting of complex numbers. In recent years, CVANN has increasing interest because CVANN gives better results in nonlinear signalprocessing and image processing problems. There has been no software introduced in the literature for CVANN yet. In this study, CVANN software (CV-ANN), which is developed with object-oriented programming language C#, is presented. In this software tool which is designed with a user-friendly interface, user can set the parameter values of CVANN.

Changes in neural network output with respect to entered parameter values are showed graphically. Developed software can facilitate the work of researchers in academic and scientific studies. At the same time, this software can be useful as an educational tool in the sense of making the working mechanism of CVANN clearer. CV-ANN is tested on XOR problem which is a standard test and CV-ANN proves its reliability performing the classification with the accuracy obtained by the same algorithm in the literature.