Neural networks need data to learn, even if it’s fake (quantamagazine.org) | HN Screenshots

YHacker Newsscreenshots

Screenshot of quantamagazine.org: Neural networks need data to learn, even if it’s fake

First screen, captured 3 years ago.

Looks similar

Screenshot of quantamagazine.org: Parallels in the ways that humans and ML models acquire language skills

Parallels in the ways that humans and ML models acquire language skills (quantamagazine.org)

94 points by theafh 3 years ago | 24 comments

Screenshot of quantamagazine.org: Kolmogorov-Arnold networks may make neural networks more understandable

Kolmogorov-Arnold networks may make neural networks more understandable (quantamagazine.org)

263 points by isaacfrond 2 years ago | 77 comments

Screenshot of quantamagazine.org: A New Approach to Computation Reimagines Artificial Intelligence

A New Approach to Computation Reimagines Artificial Intelligence (quantamagazine.org)

47 points by theafh 3 years ago | 25 comments

Screenshot of quantamagazine.org: Language models still struggle with the concept of negation

Language models still struggle with the concept of negation (quantamagazine.org)

111 points by belter 3 years ago | 102 comments

Screenshot of quantamagazine.org: AI Needs Enormous Computing Power. Could Light-Based Chips Help?

AI Needs Enormous Computing Power. Could Light-Based Chips Help?(quantamagazine.org)

41 points by jolieli 2 years ago | 28 comments

Screenshot of quantamagazine.org: Cynthia Rudin and interpretable ML models

Cynthia Rudin and interpretable ML models (quantamagazine.org)

60 points by SirLJ 3 years ago | 45 comments