Akarsh Kumar: belief

Transcript context

…hing, like, it's not even that interesting. But it's actually really remarkable from a genetic algorithm perspective because preservation of regularities like that is not at all a foregone conclusion. Like, in a regular genetic algorithm, you're messing things up on every single mutation. You don't get this really high probability of preserving some deep underlying regularity. Like, that that would be that would be incredible if you were having such a fortuitous set of offspring that they all preserve some really important aspect. But what's happened in the representation in nature, the way DNA has become organized, the way that the genetic regulatory network works, you know, as a hierarchy, is that it's been and biologists use the word canalized or canalization. It's been canalized. It's like it it dug a trench into a mountainside and created a canal so that if there is a change, like a mutation or an earthquake in the analogy, you still get the water to run down through the same canal, and that's the developmental pathway, like, with the bilateral symmetry and the other regularities. Like, you have arms, you have you have you have legs. It's true. Obviously, there's a miscarriage rate, but it's incredibly low compared to, like, the, like, general destruction of the phenotype that you see in a traditional genetic algorithm. And there are things you never see. Like, you never see trilaterally symmetric offspring and things that could happen. Like, if you were using, like, an indirect encoding or something like an l system in a traditional genetic algorithm, like, which can express body plans, like, you can get it's very easy to go from bilateral to trilateral or 5 fingers to 10 fingers, like, in a single jump. Like, it never happens in biology. So biology has learned underlying regularities, just like the underlying pick breeder genome for the skull. There's a strong analogy. And why does that matter? It matters because it shows as a proof of concept that there are forces in nature that are not guided by humans, that similarly because of the divergent aspect of the search, the serendipitous aspect, open ended aspect of the search, similarly similarly also do end up with representations that arguably are approaching what we're calling a unified factored representation in the paper. And so it gives hope that there may be algorithmic interventions that are possible independent of human users, like making selections themselves, that could could do something similar to representation because we also see in nature, in a in a sense, in an automated environment, but not an objectively driven 1 in the traditional sense. A lot of people in ML thinks think that we perfectly understand evolution and that is just like, know, genetic algorithm. I think Ken would agree with the statement that if we really were to understand it, then we should have, then there should be exist like an algorithm that we can scale up right now that can recreate all the glamour of evolution. Right? All the flights, photosynthesis. There's not a single algorithm that can that we can scale up that we can definitively say that will, like, do what evolution did in the current, state of genetic algorithms, ML. Would you agree with that, Ken? Yeah. Yeah. I mean yeah. So if that's true, that means that we don't really fully under, like, stand and we understand aspects of it, like Ken's amazing work on, like, open ended serendipity. But we don't have a full picture of, evolution. And that's why genetic algorithms are nowhere close to a full picture, and we don't really understand everything that evolution is doing. Agreed. Yeah.…

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