Pedro Domingos: evaluation

Transcript context

…First of all, shout out to Tim Rocktaschel. I I read that blog post from 2000 and earlier that that you were referring to. But I suppose the thought occurs that if it is mostly about Einsam and, you know, you might make the argument why do we need an abstraction when we already have a great abstraction in EINSUM. So folks now can use PyTorch and, you know, JAKs. What what exactly does your abstraction allow them to do that they can't do with PyTorch? No. Very good. It does several things. So first of all, and this is gonna be an increasing order of importance, the syntax of einsum in this language, there's also this package called inops, is incredibly clunky. So at a very basic level, tensor logic is just a much pithier, more compact, easier to write and understand way to write einsums. And you know, physics and mathematicians famously like to say that a good notation is half the battle. So this might not seem like a big deal, but my experience is that you can just think better and faster once you have this notation that like this funky procedure call with these indices and these arrows and these arguments. It's a nightmare and you know, the syntax of tensor logic is like you write a ninth sum like you would write a rule. There's a tensor equation with a tensor on the left hand side and and and and this join of tensors on on on on the on the right on the right hand side. Right? So this is 1 aspect. Another very important aspect and 1 that I think could prove decisive is that people don't use ions so much because it's not very efficient. Under the hood, it's not as efficient as you tip, you know, sometime I you know, this could be done so much better. Right? But I've done some of programming of this and I wound up even I wound up not using Einstein because it's so slow and clunky. And all of that can be fixed. Once you have this 1 abstraction of the tensor equation and you implement it on CUDA, for example, you can optimize the heck out of it and you'll just be able to, you know, Einstein will finally be able to reach its potential. Right? But actually none of these things actually the most important part. The most important part is that the the Einstein as we know it is only good for for for tensor algebra. Tensor logic is a language where the same construct does all the symbolic and all the the numeric parts and and any mix and variation between them including learning the symbolic part and whatnot. These are all things that in world just didn't exist. Right? You talk about the people in Einstein whether in AI or mathematics or physics and they just had no idea that any of this had anything to do with reasoning. You look at all the ways that people are trying to do reasoning today and just wanna pull out your hair. Let me ask a very concrete, you know, in some sense, I'm a simple simple man. I need, like, a very concrete example because I completely agree with you, which is that the symbols we use, the language we use are just simplicity is so fundamental to our ability to, like, reason at higher and higher levels. So let's take 1 example, you know, from your paper, which is a logical or logical or of a bunch of values is equivalent to an EIN sum within a Heaviside, you know, function applied to it. Like you give this example. Right?…

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