Custom regression layer in Deep Learning Toolbox

Hi.

I have a quick question about "Custom Regression Output Layer."_ https://www.mathworks.com/help/nnet/ug/define-custom-regression-output-layer.html

My goal is similar to this: https://www.mathworks.com/help/nnet/examples/train-a-convolutional-neural-network-for-regression.html

My understanding is that, in the first step, a batch of images goes through the network and compute the loss by learning a function of the forwardloss. However, I realized that MATLAB runs a function of the backwardloss first.

Could you explain why the backwardloss runs first?

Chulmin

[NM]

Hi Chulmin, I am using the same example to forecast electricity demand. However, I couldn't translate the example to make it usable with my data as my data doesn't contain images. Can you please help me out? My data: Xtrain (9x800) double type, Ytrain (1x800)

[Chul Min Yeum]

Could you more elaborate your data and purpose? Cnn is designed for image data. You can simply use a neural network toolbox for your problem.