Um, but spiking networks are notoriously more difficult to train.

Yeah.

Um, so I think they're getting easier and easier.

And actually this, uh, I think Dan Goodman posted this on blue sky, like a few weeks ago.

And there was a discussion about why, uh, it's a great time to work with spiking networks.

And it's because the methods to train them are actually pretty good now.

So I did do some balance spiking network stuff during my PhD and just felt like I'm never going to get these things to do computation, so I might as well switch over to rate-based networks.

mocking Monte and Cecilia.