High Signal Podcasts Evidence ledger
Method
Browse

Public evidence record

Andrew Gordon Wilson

Published podcast speaker

Claims
21
Episodes
1
Shows
1
Named items
0

Claim ledger

What Andrew said.

7 transcript-backed records

02 / evaluation

Whereas in fact, as we build bigger models, we often actually start to alleviate overfitting. And double descent is just a great example of this because that first ascent is is from overfitting the data.

“Whereas in fact, as we build bigger models, we often actually start to alleviate overfitting. And double descent is just a great example of this because that first ascent is is from overfitting the data.”
Publisher
Machine Learning Street Talk

03 / evaluation

Like, once a certain number of people believe something, it's very, very hard to change their minds no matter what you say. And I think as a consequence, we've been in all sorts of local minima in machine learning and AI research because we haven't been able to get unstuck from these erroneous beliefs.

“Like, once a certain number of people believe something, it's very, very hard to change their minds no matter what you say. And I think as a consequence, we've been in all sorts of local minima in machine learning and AI research because we haven't been able to get unstuck from these erroneous beliefs.”
Publisher
Machine Learning Street Talk

04 / evaluation

A, because it's not an honest representative of our representation of our beliefs to to have those hard constraints, and b, because we see in practice that when we do have these expressive models with simplicity biases, they're much more adaptive.

“A, because it's not an honest representative of our representation of our beliefs to to have those hard constraints, and b, because we see in practice that when we do have these expressive models with simplicity biases, they're much more adaptive.”
Publisher
Machine Learning Street Talk

05 / evaluation

Because that means there are gonna be many more different settings of parameters that are consistent with what we observe, and we're just betting everything on 1 of them.

“Because that means there are gonna be many more different settings of parameters that are consistent with what we observe, and we're just betting everything on 1 of them.”
Publisher
Machine Learning Street Talk

06 / evaluation

ence on materials engineering and things like that, I'll see lots and lots of talks using Bayesian optimization, Gaussian processes, neural networks with epidemic uncertainty representation, etcetera. So this is really useful in practice, but it's very hard to kind of go beyond the useful approximations I think we developed without doing a significantly without making sort of a really significant, you know, 10 year kind of style moonshot landing kind of investment in those directions, which I think is worth making.

“ence on materials engineering and things like that, I'll see lots and lots of talks using Bayesian optimization, Gaussian processes, neural networks with epidemic uncertainty representation, etcetera. So this is really useful in practice, but it's very hard to kind of go beyond the useful approximations I think we developed without doing a significantly without making sort of a really significant, you know, 10 year kind of style moonshot landing kind of investment in those directions, which I think is worth making.”
Publisher
Machine Learning Street Talk

07 / evaluation

Representation meaning sort of how you're solving the problem even if you're getting the same performance in a particular application. But the reason it matters is because different representations that are achieving the same performance might give you different performance than on different problems.

“Representation meaning sort of how you're solving the problem even if you're getting the same performance in a particular application. But the reason it matters is because different representations that are achieving the same performance might give you different performance than on different problems.”
Publisher
Machine Learning Street Talk
Search evidence