Where Transfer Learning from A to B Makes Sense

1. Task A and B have the same input X.
2. You have a lot more data for A than B.
3. Low level features in A could be helpful for learning B.

Where Multi-task Learning Makes Sense

1. Training on a set of tasks that could benefit from having shared lower-level features.
2. Usually: Amount of data you have for each task is quite similar.
3. Can train a big enough neural network to do well on all the tasks.