What Is a Neural Network: How AI Learns From Data
A neural network is an AI system inspired by the brain, built from layers of connected nodes that learn patterns from data to make predictions.
What has been corrected on this page?
Every accepted correction to this page is recorded with the exact change, so readers can see how the page improved over time.
-
2 corrections applied: ARC-AGI benchmark was created by Francois Chollet (then at Google), not Marcus Hutter at DeepMind. | The GraphCast 90.3%/1,380-targets result is from DeepMind's GraphCast paper (Lam et al., Science 2023), not an LSE study by Erica Thompson.
Before(1) "Marcus Hutter at DeepMind developed the ARC-AGI benchmark..." (2) "Erica Thompson at the London School of Economics and colleagues published research...examining GraphCast...90.3 percent of 1,380 test targets"
After(1) "Francois Chollet at Google and colleagues developed the ARC-AGI benchmark to measure whether neural network capabilities constitute general intelligence rather than narrow pattern matching." (2) "Remi Lam at Google DeepMind and colleagues published research in 2023 examining how neural network weather prediction models compared to operational numerical weather prediction systems... Google DeepMind's GraphCast system... achieved better forecast accuracy on 90.3 percent of 1,380 test targets"
Why: Verified: body text correctly attributes the ARC-AGI benchmark to Francois Chollet at Google, and the GraphCast 90.3%/1,380-targets result to the Google DeepMind team (Lam et al., Science 2023), not to a London School of Economics study. No stale Marcus Hutter/DeepMind or Erica Thompson/LSE attributions remain anywhere on the page (there is no separate bibliography section on this article), and the FAQ schema does not reference either citation. No further changes needed.
View the full record →
Who checked this page?
1 contributor has checked "What Is a Neural Network: How AI Learns From Data" on When Notes Fly. Each name below links to that person's public CitePep profile, where every contribution they have made is listed with the exact change they proposed.