A neural network performing both regression and classification

Hi,

I would like to build a neural network input matrix of [12*1000], i.e., 1000 samples, each with 12 fields and an output matrix of [3*1000], i.e., 1000 samples, each with 3 fields . However, I want that 1st and 3rd output field have integer values in a specific range ( neural network is performing classification) and the second field i has decimal values in [0,1] ( neural network is performing regression). How can I do this ?

Thanks in advance

Answer 1

[Srivardhan Gadila]

In Deep Learning Toolbox™, you can define network architectures with multiple inputs (for example, networks trained on multiple sources and types of data) or multiple outputs (for example, networks that predicts both classification and regression responses). Refer to Multiple-Input and Multiple-Output Networks