High Signal Podcasts Evidence ledger
Method
Browse
How the evidence works

Public evidence record

Andrew Gordon Wilson

Published podcast speaker

Claims
21
Episodes
1
Shows
1
Named items
0

Claim ledger

What Andrew said.

8 transcript-backed records

01 / belief

There was a paper that looked at something briefly like this called Intelligence at the Edge of Chaos, and I think there are other results like that that are coming out that you actually might want to train your models on this data with a lot of structural complexity, even if you really want in the end the model has some kind of outcomes, razor bias, etcetera.

“There was a paper that looked at something briefly like this called Intelligence at the Edge of Chaos, and I think there are other results like that that are coming out that you actually might want to train your models on this data with a lot of structural complexity, even if you really want in the end the model has some kind of outcomes, razor bias, etcetera.”
Publisher
Machine Learning Street Talk

02 / belief

Do we understand how the brain works? And this is sort of a conventional sort of like approach to science where the theory is really the quantity of primary interest and the applications of course are important, but they're not primarily why like no individual application is primarily why we care about the theory.

“Do we understand how the brain works? And this is sort of a conventional sort of like approach to science where the theory is really the quantity of primary interest and the applications of course are important, but they're not primarily why like no individual application is primarily why we care about the theory.”
Publisher
Machine Learning Street Talk

03 / belief

I think although the field has made an extraordinary amount of empirical progress towards building more performant machine learning systems, We're still at early stages of understanding, you know, what principles should we broadly embrace when we're approaching our own problems.

“I think although the field has made an extraordinary amount of empirical progress towards building more performant machine learning systems, We're still at early stages of understanding, you know, what principles should we broadly embrace when we're approaching our own problems.”
Publisher
Machine Learning Street Talk

05 / belief

Hopefully, they'll be able to go back and read not just my work, but like work that's been done in this space and think, okay, this is useful to me in thinking about how to approach some of these questions. And so, in this respect, I would say I'm a scientist and I try to combine classical theory with empiricism towards understanding model behavior.

“Hopefully, they'll be able to go back and read not just my work, but like work that's been done in this space and think, okay, this is useful to me in thinking about how to approach some of these questions. And so, in this respect, I would say I'm a scientist and I try to combine classical theory with empiricism towards understanding model behavior.”
Publisher
Machine Learning Street Talk

06 / belief

Like the models get both more expressive and they have a stronger simplicity bias. And so I think you can expand these 2 things together in some sense, and this is how you can avoid say overfitting and other sorts of issues with not achieving very good generalization.

“Like the models get both more expressive and they have a stronger simplicity bias. And so I think you can expand these 2 things together in some sense, and this is how you can avoid say overfitting and other sorts of issues with not achieving very good generalization.”
Publisher
Machine Learning Street Talk

07 / belief

I think 1 of the most surprising findings in that paper was that convolutional neural nets, which were clearly designed for image recognition, so they have locality and translation equivariance and so on, provably have inductive biases for tabular data shaped as And an the only possible reason that could be the case is because they both sort of share this bias for low Kolmogorov complexity.

“I think 1 of the most surprising findings in that paper was that convolutional neural nets, which were clearly designed for image recognition, so they have locality and translation equivariance and so on, provably have inductive biases for tabular data shaped as And an the only possible reason that could be the case is because they both sort of share this bias for low Kolmogorov complexity.”
Publisher
Machine Learning Street Talk
Search evidence