News for hackers. Stuff that matters.
Re:A Separate Kind of Intelligence by ssivark on Saturday October 05, 2019 @12:16PM (#21166305)
Not really. A model (after training) continues to be as plastic as it was before. Correspondingly, it can be made to "forget" what it has "learned" and learn something else. [At least architecture-wise. Whether the learned parameter values reduces plasticity is a non-trivial statement that needs to be demonstrated]

If contemporary AI/ML models behaved like what Alison Gopnik says, then their tendency to overfit would be even more of a problem -- you couldn't even transfer them from simulation domain to reality -- since they would lose all their plasticity overfitting to simulation!

Also, this article contains lots of other interesting ideas to think about. Highly recommend reading all of it.

Re:A Separate Kind of Intelligence by personjerry on Saturday October 05, 2019 @02:40PM (#21167162)
The learning coefficient decreases over time making the model less plastic.
Re:A Separate Kind of Intelligence by vankessel on Saturday October 05, 2019 @03:30PM (#21167432)
Only because you have chosen for the learning rate to decrease over time so the model converges. You could reset it.

I would even argue the LR is not relevant to plasticity, it's a meta-variable for training the model and not to do with the model itself.

A plastic model would be one that could accomplish a given task after being trained on it, and then trained on a second task while maintaining the ability to accomplish the first task.