TGViewer
Linkstream Linkstream @linkstream · 169 subscribers
Post #550 206
Human-level concept learning through probabilistic program induction
[abs] https://www.semanticscholar.org/paper/Human-level-concept-learning-through-probabilistic-Changala-Mellau/23078c79c0fc425653aeafcee2ddd01210254658
[pdf] https://cims.nyu.edu/~brenden/LakeEtAl2015Science.pdf
via @senchaid
www.semanticscholar.org Human-level concept learning through probabilistic program induction - Semantic Scholar People learning new concepts can often generalize successfully from just a single example, yet machine learning algorithms typically require tens or hundreds of examples to perform with similar accuracy. People can also use learned concepts in richer ways…
Open in Telegram All posts from @linkstream
More from @linkstream
  1. Oct 6, 2026https://fixupx.com/capacitanas/status/2107153559427145785?s=46
  2. Sep 30, 2026i started doing exactly this (models editing its own context) as a natural extension of sa…
  3. Sep 28, 2026cursed font factory https://bastardica.mitpit.com/
  4. Sep 25, 2026um, ahem, AlphaZero for text. Training language models without language. Loosely, natural…
  5. Sep 23, 2026umm ahem if you don't try to rein in new opus(5.5) you get one more qualitative step in ca…
  6. Sep 23, 2026nice https://fixupx.com/eyalsela/status/2102373749110587443?s=46
Threads Profile ViewerView any public Threads profile without an account.Open ThreadLook →Writing with AI? Make it sound human.Metric37 rewrites AI drafts so they read naturally. Free AI detector, 1,500 words free.Try Metric37 →