custom multiple output regression

Hi

i want a way to solve 'custom multiple output regression'

i just want to see a simple example code. I can't find examples because my googling skills aren't good.

I hope that someone who is very generous can leave even a simple example code.

'custom multiple output regression'

layer structure etc...

Thank you for reading my quesion!

Answer 1

[Iuliu Ardelean]

layers1 = [
    imageInputLayer([21 21 1],"Name","imageinput")
    convolution2dLayer([3 3],32,"Name","conv_1","Padding","same")
    batchNormalizationLayer("Name","batchnorm_1")
    leakyReluLayer(0.01,"Name","leakyrelu_1")
    convolution2dLayer([3 3],32,"Name","conv_2","Padding","same")
    batchNormalizationLayer("Name","batchnorm_2")
    leakyReluLayer(0.01,"Name","leakyrelu_2")
    convolution2dLayer([3 3],32,"Name","conv_3","Padding","same")
    batchNormalizationLayer("Name","batchnorm_3")
    leakyReluLayer(0.01,"Name","leakyrelu_3")
    fullyConnectedLayer(8,"Name","fc") % <- 8 outputs
    regressionLayer("Name","regressionoutput")];

Read: https://uk.mathworks.com/help/deeplearning/ug/train-a-convolutional-neural-network-for-regression.html

[jaehong kim]

Thank you for your answer.

However, I want a neural network layer that receives 8 features and outputs 8(or 1) output.

In other words, i want something about DNN. It seems that your answer is CNN.