Pedro Domingos: belief

Transcript context

…I I I do. But could I could I challenge it a tiny bit? So when when we train neural networks, we we think reasoning is good when we are building, you know, let let's say we use the Lego analogy. So we're we're building these blocks and the new understanding tree that we've created is a good 1 if it represents the world in an abstract causal way. So I can see how you've, you know, framed this as deduction in the sense that, you know, you've you've you've got this boolean operation and and you can you can build from it. But what if you're building on a sand castle? What if the what if the component, let's say it's an MLP component, what if it just doesn't represent the way the world works? No, no. So very good. So like again, there's more than 1 thing you can do with tensor logic. 1 of them is you can just reimplement existing things like MLPs and transformers and whatnot. And if all that you did was reimplement them, it will have all their pros and cons, right? It's the same thing, just implement it much more elegantly, blah blah, right? What I'm talking about here, and talk about in that section of the paper, is doing something different. It's not an MLP, it's not a transformer. It's actually doing these things of like, you embed objects, you embed relations in a certain way that falls from the object, you embed the rules, you embed the reasoning, right? So this is a different process. What this different process allows you to do is that when you raise the temperature, you get to do analogical reasoning. You know, we you know, Douglas Alstadter came up before. Douglas Alstadter I think would like this because it's it's an analogical like he has this whole 500 page book arguing that all of cognition is just analogy. Right? And again, this is 1 of the schools of thought, like this is 1 of the tribes in, you know, in the master algorithm is reasoning by analogy. You do reasoning by analogy because what happens is you generalize from from from 1 object to an object that has a high dot product with it. So now now I'm I get to borrow inferences from similar objects. And the higher the temperature the the looser the inferences, the more analogical inference can be. But for example, and again Douglas goes goes into this in some of his book, and any mathematician like I just, you know, Terrence Tout the other day, I just heard him say this, right, is like mathematicians reason by analogy. They notice similarities between things. But at the end of the day you need to have a proof. Intensive logic in this scheme, in this particular scheme of of embedding, you know, reasoning in embedding space, this is just simulated annealing. You start out with a high temperature being very analogical, and then you lower it. At the end of the day, you have a proof. It's a deductive proof that is guaranteed to be correct. But you couldn't have gotten to it because the search space is so large without the analogical part. Right? Okay. But I I understand what you're saying. So you you can generalize reasoning outs, you know, outside the domain of certainty. But the question I'm asking, the reason why we have metaphor and analogy is there's this incredible process of evolution and intelligence and it's led to the coarse graining of all of these concepts that we use in our language and there's this rich beautiful phylogeny that kind of represents the causal reality of what's happened and why is statistical similarity the same thing as analogy?…

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