Refer to the following links to get the required information-
https://www.mathworks.com/help/nnet/ug/introduction-to-convolutional-neural-networks.html
https://www.mathworks.com/help/nnet/ug/layers-of-a-convolutional-neural-network.html
It gives an example of transforming 3D input to 3D output. A smaller network with only one or two convolutional layers might be sufficient to learn a small number of gray scale image data. On the other hand, for more complex data with millions of colored images, you might need a more complicated network with multiple convolutional and fully connected layers.
