I'm using fitrgp toolbox for Gaussian process Machine learning on MATLAB. But till now all my work has been in real numbers. Now I need to include complex numbers in my project. But fitrgp does not accept complex training data. Is there any way to get around this situation, like a substitute toolbox or some way to include complex numbers in the same toolbox?
The complex numbers can be implemented using their arguments and angles. Sometimes the arguments are adequate, otherwise the two values can be used.
Can you elaborate in what context you are trying to use complex values? If you are working with spatial domain, for example, you can perform a coordinate transformation and obtain equivalent real values. So, it really depends on what data you are working with.
- Badges
- Science topic