Peter Norvig - The Unreasonable Effectiveness of Data

Поділитися
Вставка
  • Опубліковано 9 лис 2024

КОМЕНТАРІ • 33

  • @user-kj8qy6ek6n
    @user-kj8qy6ek6n 8 місяців тому

    came across this in my junior year in college, was really inspired and I actually decided to do a master in machine learning because of this. Thank you Mr.Norvig!

  • @KaplaBen
    @KaplaBen 5 років тому +3

    0:11 "you'll have to make do with me". Love the humility and self-deprecating humor

  • @saifuddinraja
    @saifuddinraja 2 роки тому

    this is so underrated , needs more views

  • @gabrieltenenbaum
    @gabrieltenenbaum 8 років тому +8

    It's funny because the video is amazing, there are great insights about data science and all, however, if one turns on the automatic subtitles, it has mostly nothing to do with what he's actually saying.

    • @datalicious43
      @datalicious43 7 років тому +2

      Caused they trained the base model using neutral accent , not American . :):)

  • @rangjungyeshe
    @rangjungyeshe 12 років тому +1

    Very interesting insights in how comp sci is now using inference from data to solve problems previously tackled by rules. Maybe this is closer to how humans learn languages....it sure isn't by learning all that grammar...

  • @pablo_brianese
    @pablo_brianese 3 роки тому

    Beautiful work!

  • @pleabargain
    @pleabargain 11 років тому

    15:27 predicting the present... very powerful

  • @pablo_brianese
    @pablo_brianese 3 роки тому +1

    39:45 You can bet Borges understood exponential growth, given he knew enough mathematics to understand the theory of transfinite numbers.

  • @pleabargain
    @pleabargain 11 років тому

    28:30 the spelling corrector function described

  • @57v60n85t
    @57v60n85t 12 років тому

    Although it is an enlightening talk, the graph at 52:00 is slightly misleading. If you set the lower limit of y-axis to zero, you will see what I mean.

    • @DominickGuzzo
      @DominickGuzzo 6 років тому

      Aren't you assuming that there's little value in the difference of ~48% vs ~53% accuracy? Depending upon the scenario, incremental improvement like that can be quite valuable.
      Imagine a similar chart for, say, website uptime: What would it look like with 99.9% plotted against 99.999999% when the y-axis starts at zero? Is that a useful visual?

  • @pleabargain
    @pleabargain 11 років тому

    25:50 a bit of levity with word play

  • @pleabargain
    @pleabargain 11 років тому

    19:07 define the function that will read smashed words

  • @pleabargain
    @pleabargain 11 років тому +1

    26:45 harder problems spelling corrections

  • @pleabargain
    @pleabargain 11 років тому

    21:29 the code for his parser. It looks like Python but not commented correctly.

  • @pleabargain
    @pleabargain 11 років тому

    32:30 the python code for his spell correction app

  • @pleabargain
    @pleabargain 11 років тому

    12:42 how to do orbital mechanics just using text!

  • @pleabargain
    @pleabargain 11 років тому

    49:00 questions from the audience

  • @AnimeshSharma1977
    @AnimeshSharma1977 10 років тому +4

    brain behind the Google translate ;)

  • @JGunlimited
    @JGunlimited 10 років тому

    o_0! Norvig is amazing!

  • @pleabargain
    @pleabargain 11 років тому

    11:22 Google's corpus of N grams... 13M+ unique words...

  • @pleabargain
    @pleabargain 11 років тому

    4:15 expert system approach to learning

  • @thinley108
    @thinley108 12 років тому

    part starting 24:50 is very funny

  • @pleabargain
    @pleabargain 11 років тому

    18:13 let's read Chinese!

  • @pleabargain
    @pleabargain 11 років тому

    5:03 Image models and then text models. Image models first.

  • @pleabargain
    @pleabargain 11 років тому

    10:20 Text models

  • @pleabargain
    @pleabargain 11 років тому

    6:50 first problem is scene completion

  • @pleabargain
    @pleabargain 11 років тому

    8:05 Old CS school method of solving problems...

  • @pleabargain
    @pleabargain 11 років тому

    4:44 Statistical machine learning Judea Pearl see his wikipedia page

  • @pleabargain
    @pleabargain 11 років тому

    10:36 props to Frederick Jelinek see wikipedia.