Karl Friston - 2016 CCN Workshop: Predictive Coding

Поділитися
Вставка
  • Опубліковано 28 січ 2025

КОМЕНТАРІ • 31

  • @CharlesVanNoland
    @CharlesVanNoland 6 років тому +6

    The content of this presentation is pure gold.

  • @MLDawn
    @MLDawn 2 роки тому

    05:41 is the main part that shows why RL type approaches cannot work in certain situations. I just loved it!

  • @abdurhmanalzayed9429
    @abdurhmanalzayed9429 6 років тому +5

    this man is genuis..the implication of his revolutionary theory Free Energy principle will unfold in the near future.

  • @alfcnz
    @alfcnz 3 роки тому +1

    Link to the slides?

  • @MirrorNeuron
    @MirrorNeuron 2 роки тому +1

    Hi all, where can I learn the math used in this presentation, like translating the real world observation into math? Is there a book, or a tutorial for a novice like me.

  • @olgierdborowiecki2424
    @olgierdborowiecki2424 7 років тому +6

    This video lacks of zooming the presentation :/

  • @zhihengxu5011
    @zhihengxu5011 4 роки тому

    optimal action function 6:35; Baysesian suprise 10:53

  • @Lleruelu
    @Lleruelu 6 років тому

    Thanks so much for sharing

  • @greyreynyn
    @greyreynyn 6 років тому +1

    48:30 savage 'ahh your question is trivial'

  • @valueengines2184
    @valueengines2184 4 роки тому

    The answer to the last unanswered question: "what about surprise seeking" is that when exploitation is complete, the explorer is bored. The rat then seeks surprise to avoid boredom.

  • @Gerardemful
    @Gerardemful 4 роки тому +1

    I used to admire Mr. Friston until he outed himself as a cheap nationalist in his Guardian interview.

    • @khwajawisal1220
      @khwajawisal1220 4 роки тому +2

      what did he say, i read the interview, and he was very cautious with his choice of words and just presented his results. @Hans Richter

    • @snippletrap
      @snippletrap 3 роки тому +1

      Cheap nationalists are the worst kind.