Pedro Domingos: evaluation

Transcript context

…Alright. So let me let me push back on something because you mentioned it twice now, which is like the Turing completeness. So your paper relies on, like, Siegelman's, you know, 1995 sort of paper. She herself now, like decades later, has admitted that that thing is a total toy that has no practical relevance whatsoever. Okay? Because it requires, like, infinite precision, rational, registers that encode in a fractal way, etcetera. And by the way, in her paper, all she demonstrated was that under these infinite assumptions that she could build a particular RNN that was a universal Turing machine. The problem with you using that for your tensor logic is 2 things. 1, that restricts the field over which you can have your tensors. It must be 1 of these fields that has like infinite precision. So infinite precision rationals or whatever. I can't use any other fields like no modular arithmetic, which is actually what runs on, you know, GPUs for example. And secondly is it would restrict the actual structure of the weights to her universal Turing machine. Therefore, it wouldn't be a general purpose tensor logic. Well Do you realize this problem? No. No. No. So actually there is no problem there. Let me tell you exactly why. Right? And let's just do this in 3 steps. First of all, tuning completeness doesn't matter at all whatsoever. Because the only difference between a turing machine and a finite state machine is the infinite tape. And in the real world, there is no infinite tape. So if you can implement matter why do you keep mentioning it?…

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