home.social

#machinelearnning — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #machinelearnning, aggregated by home.social.

fetched live
  1. 👍🏻 GPT-4 is here – join the live demo for developers at 1 pm PDT ! 🪄 #GPT4 a large multimodal model!

    - You can use images as inputs and generate captions, classifications, and analyses.

    - It can generate/edit creative and technical writing: songs, screenplays, or learn a writing style.

    - It can handle 25,000+ words. it passes a simulated bar exam with a score around the top 10% of test takers. openai.com/research/gpt-4 #MachineLearnning

  2. DARPA is accepting applications to attend a virtual event June 13-16, 2023 and an in-person event in Boston July 31-August 2, 2023 in which participants will address the question: How do we build artificial intelligence and machine learning systems that people can trust?

    #ai #darpa #artificialisation #MachineLearnning #research

    darpa.mil/news-events/2023-02-

  3. DARPA is accepting applications to attend a virtual event June 13-16, 2023 and an in-person event in Boston July 31-August 2, 2023 in which participants will address the question: How do we build artificial intelligence and machine learning systems that people can trust?

    #ai #darpa #artificialisation #MachineLearnning #research

    darpa.mil/news-events/2023-02-

  4. What learning algorithm is in-context learning? Investigations with linear models arxiv.org/abs/2211.15661
    …investigates the hypothesis that transformer-based in-context learners implement standard learning algorithms implicitly, by encoding smaller models in their activations, and updating these implicit models as new examples appear in the context.

    #MachineLearnning #DataScience

  5. What learning algorithm is in-context learning? Investigations with linear models arxiv.org/abs/2211.15661
    …investigates the hypothesis that transformer-based in-context learners implement standard learning algorithms implicitly, by encoding smaller models in their activations, and updating these implicit models as new examples appear in the context.

    #MachineLearnning #DataScience

  6. ❤️ A fast, ChatGPT-like assistant for your mac. Personalized to you — and your work. 👍🏻 Your personal, intelligent AI — always one second away! #Embra can pull in contextual data from #Chrome and other apps to speed up and unlock creativity across Q&A, brainstorming, writing, reading, and coding.

    Get beta access! embra.app/ #MachineLearnning

    #productivity #apple #macos

  7. 👍🏻 10X Your Productivity in Excel with ChatGPT - You no longer have to be an Excel wizard to become super productive. link.medium.com/MUWC4FOTXwb #MachineLearnning #productivity #microsoft

  8. rizbicki.ufscar.br/ame/
    Izbicki, R. e Santos, T. M. dos. Aprendizado de máquina: uma abordagem estatística. 1ᵃ edição. 2020. 272 páginas. ISBN: 978-65-00-02410-4 #AprendizadoDeMaquina #MachineLearnning

  9. rizbicki.ufscar.br/ame/
    Izbicki, R. e Santos, T. M. dos. Aprendizado de máquina: uma abordagem estatística. 1ᵃ edição. 2020. 272 páginas. ISBN: 978-65-00-02410-4 #AprendizadoDeMaquina #MachineLearnning

  10. Just a couple of hashtags to attract like minded people to hang out on #mastodon :
    #deeplearning #MachineLearnning #medicalimaging #BioImageAnalysis #math #statistics .....
    Folks, if you work with above topics ( and science in general), I'd love to follow you!

  11. Just a couple of hashtags to attract like minded people to hang out on #mastodon :
    #deeplearning #MachineLearnning #medicalimaging #BioImageAnalysis #math #statistics .....
    Folks, if you work with above topics ( and science in general), I'd love to follow you!

  12. @[email protected] not doing research but I apply in , in particular . For example, In my last project I used to solve the inverse problem of retrieving the phase of electron wavefunctions from diffraction patterns.

  13. @chrisalbon gotta wrangle folks with hashtags, so hey and folks, any recs?

  14. Been expanding work benchmarking against more standard classification methods.

    Here’s a comparison of training accuracy on Census data as a function of training set size. produces equal accuracy to TabPFN’s max training size using just 500 records - half(!) as many!

    XGB does 1.5% better on an equal training set size (1024), and 5% better using the full data (30k points).