Do the terms multi-task and multi-output refer to the same thing in the context of deep learning (with neural networks)? For example, do neural networks for multi-task learning use multiple outputs?
If not, what is the difference between them?
It would be helpful if you can also give examples.
I found some of the terms here. When I went to study this term on the Internet, I found it very convoluted, as different authors are found to be mixing up those terms.