- Simply go to APPS>Machine learning>Regression learner.
- Choose the input and output data.
- set the number of hidden neurons. (vary by +-5 or 10 to check for optimum value)
- train the model and if the results aren't satisfactory repeat the process by varying neurons, learning technique, increasing data.
- If the results are satisfactory, you can export the neural network to a .m file, which can be called similar to function.
Data interpolation using ANN
10 visualizaciones (últimos 30 días)
Mostrar comentarios más antiguos
Serg
el 28 de Oct. de 2020
Comentada: Serg
el 10 de Nov. de 2020
Hi,
I am quite new to matlab. I am looking for a way to interpolate data in form of f(x,y) and f(x,y,z), so for given x and y or x,y and z I will receive third/forth value. Can you please advice what would be most convenient way to do so?
Additionally I would like to do pretty much the same activity, but using Artifical Neural Network. Frankly speaking I do not have much experience using them. I am wondering if I can use something already prepared/done by someone else, so it will not be that complicated. Toolbox maybe? I would be very glad on any help here.
Thank you in advance for help!
Best Regards :)
0 comentarios
Respuesta aceptada
Mayank Bajpai
el 28 de Oct. de 2020
For Interpolation,
For ANN,
Más respuestas (0)
Ver también
Categorías
Más información sobre Gaussian Process Regression en Help Center y File Exchange.
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!