High Signal Podcasts Evidence ledger
Method
Browse
How the evidence works

Public evidence record

Yi Ma

Published podcast speaker

Claims
8
Episodes
1
Shows
1
Named items
0

Claim ledger

What Yi said.

8 transcript-backed records

01 / evaluation

Has low dimensional structures that allow us to predict, to rule out variabilities, to predict world tomorrows, or predict world better, in essence. So in a sense that that is the ability we believe is really what intelligence is all about, at least the common intelligence we're talking about, right?

“Has low dimensional structures that allow us to predict, to rule out variabilities, to predict world tomorrows, or predict world better, in essence. So in a sense that that is the ability we believe is really what intelligence is all about, at least the common intelligence we're talking about, right?”
Speaker
Yi Ma
Publisher
Machine Learning Street Talk

06 / prediction

If you think about the whole diffusion denoising model, right, people are very popular right now to do why do we add noise to data, right, and to the whole world? Because we don't know where the distribution is, right?

“If you think about the whole diffusion denoising model, right, people are very popular right now to do why do we add noise to data, right, and to the whole world? Because we don't know where the distribution is, right?”
Speaker
Yi Ma
Publisher
Machine Learning Street Talk

07 / evaluation

The role of epsilon actually plays different roles, right? And I think definitely in the past many years, our understanding about the subject, how do we compress, how do we pursue the low dimensional structure from finite samples, it's quite our understanding about this problem has truly advanced dramatically.

“The role of epsilon actually plays different roles, right? And I think definitely in the past many years, our understanding about the subject, how do we compress, how do we pursue the low dimensional structure from finite samples, it's quite our understanding about this problem has truly advanced dramatically.”
Speaker
Yi Ma
Publisher
Machine Learning Street Talk

08 / evaluation

You never over so compression, by nature, if the operator are performing compression or denoising, which means this process will no longer overfit anything, right, if you conduct it right, if you converge, the solution will converge on the structure

“You never over so compression, by nature, if the operator are performing compression or denoising, which means this process will no longer overfit anything, right, if you conduct it right, if you converge, the solution will converge on the structure”
Speaker
Yi Ma
Publisher
Machine Learning Street Talk
Search evidence