This is a terminology question: in the context of artificial neural networks, does multi-task learning occur iff the network has more than 1 output?


2 Answers 2


Having multiple outputs is necessary but not sufficient for multi-task learning.

One task could be a multi-label classification task (e.g. is the input a picture of a human, a cat or a dog?) with one output node per target class. So a network with three outputs is performing a single task.

A second related task could be to predict what time of day the input photo was taken (e.g. morning, afternoon or night). So a multi-task network here could have six outputs defining the two tasks.

  • 1
    $\begingroup$ Thanks. In the case of the multi classification human, a cat or a dog, couldn't one argue that therr are three different tasks: task 1 is it a picture of a human? Task 2 is it a picture of a cat? Etc $\endgroup$ Jul 13, 2015 at 16:03

The multiple tasks in multi-task learning may not be explicitly distinct classes, but differing distributions of the same labels. For example, the following could all be considered multi-task learning frameworks:

Framework Input Output Single task interpretation Multi-task interpretation
Multi-class classification Image Cat, dog, fish What animal is this? Is this a cat?
Is this a dog?
Is this a fish?
Binary classification Text Spam, not spam Is this email spam? Is this English email spam?
Is this Spanish email spam?
Is this Russian email spam?

Or more explicitly, the multiple tasks may be different labels on the same underlying data (multi-label classification). Explicitly one can build a multiheaded model, where the backbone is shared amongst related (or indeed unrelated) tasks, and the heads correspond to the different tasks e.g:

Framework Shared backbone Input Output Task
Multi-headed "High level" facial features Image Head 1: binary classification
Head 2: multi-class classification
Task 3: regression
Task 1: Is this a man or a woman?
Task 2: What ethnicity is this person?
Task 3: How old is this person?

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.