본문으로 건너뛰기

Dmitry Kobak

@hippopedoid.bsky.social did:plc:tr4nc2rjorkbm4b4gpnohe4e

PI at Ghent University and VIB.AI. Manifold learning, contrastive learning, self-supervised learning, genomics, transcriptomics, interpretability. Excess mortality, statistical forensics. Born but to die and reas'ning but to err. https://dkobak.github.io

Bluesky 가입일

팔로워
335
팔로잉
67
게시물
20
순위에 오른 일수
0

요약

Dmitry Kobak(@hippopedoid.bsky.social)님은 28 11월 2024에 가입한 Bluesky 사용자입니다. 팔로워 335명, 팔로잉 67개 계정, 게시물 20개를 보유하고 있습니다.

순위 등장 기록

이 계정의 게시물이 Debya 일일 상위 목록에 오른 최고의 날들.

이 계정은 아직 일일 순위에 오른 적이 없습니다.

최근 좋아요한 게시물

Bluesky 네트워크의 공개 좋아요.

  • Karsten Konrad 🇪🇺@zabong69.bsky.social

    The arithmetic thing is a good example. LLMs learn adding numbers by representing addition as geometric operations in the NN and this can add numbers they have never seen in training. As this contradicts the stochastic parrot meme, Dr. Bender simply claims cheating and drops out of the discussion

    게시물 보기
  • Leland McInnes@lelandmcinnes.bsky.social

    UMAP 0.6 is out! A new initialization, new optimizers and faster nearest neighbour search make UMAP much faster and far better at large scale. On 3 million arXiv papers it finishes in under 5 minutes, before UMAP 0.5 has even found its nearest neighbours.

    게시물 보기
  • hikikomorphism@hikikomorphism.bsky.social

    If you can substitute "hungry ghost trapped in a jar" for "AI" in a sentence it's probably a valid use case for LLMs. Take "I have a bunch of hungry ghosts in jars, they mainly write SQL queries for me". Sure. Reasonable use case. "My girlfriend is a hungry ghost I trapped in a jar"? No. Deranged.

    게시물 보기
  • Hendrik De Bie@debiehendrik.bsky.social

    Thanks, I was a bit confused about mastodon. Yes, he has said many things over the past years that I found objectionable (even though before that did not seem to be the case). When I was younger, I found Grothendieck a bit too outspoken on certain issues, but the older I get, the more I am

    게시물 보기
  • Ryan O'Donnell@booleananalysis.bsky.social

    I lectured on the "ETH false" (#3SAT in subexponential time) result in my grad complexity class at CMU today. Didn't have time in 80 mins to do the full proof, but I hope I got across the main plan, and some of the basic TCS ingredients going into it. youtu.be/_HlQGMcQWhA

    게시물 보기

로그인하여 더 보기

차단한 계정

Bluesky의 차단은 공개 기록입니다.

이 계정은 아무도 차단하지 않았습니다.