← All source episodes Machine Learning Street Talk / episode intelligence
Making deep learning perform real algorithms with Category Theory (Andrew Dudzik, Petar Velichkovich, Taco Cohen, Bruno Gavranović, Paul Lessard)
22 Dec 2025 15 published claims 6 attributable people
Speakers in the public record
Claim mix
evaluation 6belief 2observation 2recommendation 1preference 1disagreement 1commitment 1prediction 1
Evidence policy
Every row below preserves an exact excerpt. Identified speakers are linked; unresolved voices are labeled and excluded from people counts.
Claim ledger
The useful parts, with receipts.
15 published records
“Just because we can achieve some level of moving the needle by hooking up a really potent tool to a language model doesn't mean that we shouldn't think about what would the next generation of these models look like and how can we make them intrinsically better.”
- Publisher
- Machine Learning Street Talk
“We are working in this high dimensional space, which is not necessarily easily interpretable or composable because you have no easy way of saying, for example, in in theoretical computer science, if you want to compose 2 algorithms, you're working with them in a very abstract space, which means that, you know, you can easily reason about stitching the output of 1 to the input of another, whereas you cannot make that easy of a claim about latent spaces of 2 neural networks.”
- Publisher
- Machine Learning Street Talk
“Absolutely. So if we think about a parametric morphism as as so it's a map from a to b with a parameter b, we can off we often want to change the parameter space.”
- Publisher
- Machine Learning Street Talk
“There is a school of thought that our brain works in this way. So we think using, like, the the the symbols and these categories and so on, And then there's and then there's the notion of the universe is a certain way, and we understand the universe with that kind of interface.”
- Publisher
- Machine Learning Street Talk
“The point is I only abstract what are the principles by which I can make inference on lines and their relationships to each other.”
- Publisher
- Machine Learning Street Talk
“So if you ask chat GPT, what is a bunch of eights plus a bunch of ones with a 2 at the end? It will get the correct answer because it will recognize the trick.”
- Publisher
- Machine Learning Street Talk
“I need sort of this little mechanism that when it when the wheel goes from 9 to 0, it turns the next wheel by 1. And this is very simple but it's extremely at odds with the way that GNNs have been conceived of in the past because in the past you generally, send the whole state but there's no information in the state.”
- Publisher
- Machine Learning Street Talk
“If I have a way of packing things in from a tuple into a bunch of lists, then I can pack those lists into other tuples of lists. But it's clear that this is first of all many sorted and then also differs from the group case because all of this is highly non invertible.”
- Publisher
- Machine Learning Street Talk
“Because if you have 2 things and you want to study their behavior as a composite, well, you can either study their behavior individually and look at the joint behavior, or you can compose the systems and look at the behavior of the composite.”
- Publisher
- Machine Learning Street Talk
“Why is this? It's because 2 different syntaxes can describe the same thing, very easily.”
- Publisher
- Machine Learning Street Talk
“In my PhD, I worked a lot on building, knowledge about symmetries into neural networks. And I think, for for many problems, you know, knowledge about symmetries is something that, first of all, gives you a lot of bang for the buck.”
- Publisher
- Machine Learning Street Talk
“Things like intentionality and planning and system 2 and reasoning and stuff like that, I think you're placing the assumption that there's something standard about that.”
- Publisher
- Machine Learning Street Talk
“I I I looked at it the wrong way. So I don't know what where this could go, but we are certainly striving to make things as compositional as as they could be.”
- Publisher
- Machine Learning Street Talk
“When you think about all of the big scientific advances that were done with large language models, for example, up to this date, I would argue most of the ones I'm personally familiar with are a result of a careful combination of a large language model and an algorithmic procedure in the background, which actually makes sure to give it robustness properties.”
- Publisher
- Machine Learning Street Talk
“As you can see, if you ask me to multiply 2 numbers that are, like, 50 digits long, I will definitely make some failures if you ask me to do that. But, you know, the point is that, like, what I would like is that, a system understands the amount of effort that needs to go into doing some kind of computation and maybe at least to give me some either an estimate of how likely it is to make mistakes or some notion even some notion of, I'm sorry.”
- Publisher
- Machine Learning Street Talk