Speaker unverified: uncertainty

Transcript context

…So with dictionary learning, you’re not looking for particular kind of categories. You don’t know what they are, they just emerge. Exactly. And this gets back to our earlier point when we’re not making assumptions. Gradient descent is smarter than us, so we’re not making assumptions about what’s there. I mean, one certainly could do that, right? One could assume that there’s a PHP feature and go and search for it, but we’re not doing that. We’re saying we don’t know what’s going to be there. Instead, we’re just going to go and let the sparse auto encoder discover the things that are there. So can you talk toward monosematicity paper from October last year? I heard a lot of nice breakthrough results.…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.