nekomusumeninaritai

I like it, too but there must be so many more posts there than any other community bc it is almost the only thing on my timeline.

Yes. My (minimally informed from a single class) understanding is that it sort-of depends on the problem too. Like perhaps in looking at all the data on proteins, the neural network might notice a pattern in protein folding is applicable to the tweaked problem. Of course, there is no guarantee that such a generally applicable rule exists. And even if it does, it might not be discovered by the net before overtraining occurs.

Nekomusume ni naritai!

Ah, but where do you find the training set of all of the human-written good commit messages? 😃