Explainable AI for Science and Medicine

Поделиться
HTML-код
  • Опубликовано: 1 ноя 2024

Комментарии • 37

  • @YuchengLin
    @YuchengLin 3 года назад +5

    The audience asked challenging questions because they UNDERSTAND the content. Kudos!

  • @rickyjaygomez8031
    @rickyjaygomez8031 8 дней назад

    Great questions from the audience and great explanation from the speaker. As someone working in Scientific Machine Learning where interpretability really matters, all concerns about the reliability of these XAI techniques (i.e. issues with independence among features) are valid but I think the speaker was just unable to emphasize that those are the limitations of the available techniques for XAI that we have such as SHAP, but the thing is these are the best that we have for now and those concerns are works in progress.
    There is no one-size-fits-all models and algorithms; each of them has their own advantages and disadvantages but for as long as they serve and usable in today's demand for models' interpretability, I think that is better than having nothing at all.
    Thanks for the great content! I love this :D

  • @AjaySharma-me1sy
    @AjaySharma-me1sy 2 года назад +2

    I am currently pursuing the Explainable AI course at UW and read Scott's paper as a class discussion. But I truly only understood it through this lecture, thanks for posting this!

  • @rdkap42
    @rdkap42 3 года назад +1

    My largest concern is the independence of features assumption, but this is a great talk

  • @jasonalbia5007
    @jasonalbia5007 3 года назад +4

    Very interesting talk! Highly informed audience can really be tough sometimes. Great presentation! :)

  • @griffinheart
    @griffinheart 4 года назад +10

    Great presentation, very clearly explained the concept, appreciate the great work!

  • @behnamplays
    @behnamplays 4 года назад +4

    One of the best talks I've heard in 2020. Awesome!

  • @Muuip
    @Muuip 3 года назад +5

    SHAP summaries should be integreated in all Machine Learning models. Computers can be programmed to learn and programmed to teach what and how they have learned with SHAP summaries ... diminishing inference and diminishing singularity.

  • @zhaobryan4441
    @zhaobryan4441 Год назад

    Great audience! I love the atmosphere there

  • @sakuragi9570
    @sakuragi9570 4 года назад +1

    at 35:01 with a caption on, we got a valuable meme material. Thanks Scott! Good presentation btw

  • @PantelisNatsiavas
    @PantelisNatsiavas Год назад

    Impressive lecture (and impressive audience too)

  • @andrewm4894
    @andrewm4894 5 лет назад +1

    found this talk really great, shared it with everyone!

  • @lugas2267
    @lugas2267 5 лет назад +8

    what a nice dude

  • @alphavr1315
    @alphavr1315 5 лет назад +37

    The lady always asking is really annoying...

    • @randomguy75
      @randomguy75 4 года назад

      Thank you

    • @karthiksrinivasan4923
      @karthiksrinivasan4923 4 года назад +19

      She asks great questions actually!

    • @ettoremariotti4280
      @ettoremariotti4280 4 года назад +3

      so annoying!!!!!! It really breaks the flow of the presentation

    • @bholaprasad26
      @bholaprasad26 3 года назад +6

      This is so frustrating. He is saying for 1 min then all the people asking him questions for 10 min. Why the hell they are not letting him finish the presentation and ask questions later. It's good that you are smart but being annoying is not.

    • @hoaxuan7074
      @hoaxuan7074 3 года назад +4

      A Karen.

  • @sarangakumarapeli4348
    @sarangakumarapeli4348 6 месяцев назад

    is there any method to evaluate XAI framworks results?

  • @pinakibhattacharyya7853
    @pinakibhattacharyya7853 11 месяцев назад

    Great talk

  • @KnowNothingJohnSnow
    @KnowNothingJohnSnow 2 года назад

    Wonderful presentation !!!! Thank u so mcuh

  • @senwang1982
    @senwang1982 4 года назад +1

    great work and detailed presentation. thanks for sharing.

  • @dr_flunks
    @dr_flunks 3 года назад

    Now I must have this toy... thank you!!

  • @stanzhao3606
    @stanzhao3606 3 года назад

    Haha, Susan was there as well. I detected her voice ^+^.

  • @bevansmith3210
    @bevansmith3210 5 лет назад +1

    Thanks for sharing. Really informed audience

  • @yamacgulfidanalumni6286
    @yamacgulfidanalumni6286 4 года назад +11

    Let the man talk lol

  • @vibesnovibes6320
    @vibesnovibes6320 3 года назад

    Amazing discussion 👍

  • @linlinzhao9085
    @linlinzhao9085 4 года назад

    excellent presentation, thanks

  • @anilb1076
    @anilb1076 5 лет назад +1

    can any one say what are the tools/libraries used for xai?

  • @ProfessionalTycoons
    @ProfessionalTycoons 5 лет назад

    Thank you for this talk!

  • @Muuip
    @Muuip 3 года назад

    Great presentation, much appreciated! 👍

  • @Muuip
    @Muuip 3 года назад

    Machine Learning models of Multi-omics data in combination with biology physiological and pathological mathematic and 3D models to ascertain causality in order to suggest intervention(s) on a continuous basis.

  • @EC-ve4dw
    @EC-ve4dw Год назад

    Good talk! plse speak slowly and articulate better. not understandable sometimes.

  • @Wurfenkopf
    @Wurfenkopf 3 года назад

    19:20 I'm a mathematician and, LOL!

  • @김인수-z2p
    @김인수-z2p 4 года назад

    14:53 이어보기