DeepMind x UCL | Deep Learning Lectures | 7/12 | Deep Learning for Natural Language Processing

Поділитися
Вставка
  • Опубліковано 21 лис 2024

КОМЕНТАРІ • 34

  • @leixun
    @leixun 4 роки тому +34

    *DeepMind x UCL | Deep Learning Lectures | 7/12 | Deep Learning for Natural Language Processing*
    *My takeaways:*
    *1. Plan for this lecture **0:23*
    *2. Background: Deep learning and language **3:03*
    2.1 Language applications use deep learning in very different extent 4:12
    2.2 Why is deep learning such an effective tool for language processing 7:08
    2.3 Understand languages: this is import for building language models 7:50
    *3. The Transformer **22:14*
    3.1 Distributed representation of words 23:40
    3.2 Self-attention over word input embeddings 32:13
    3.3 Multi-head self-attention 38:55
    3.4 Feedforward layer 41:57
    3.5 A complete Transformer block 42:23
    3.6 Skip connections 42:38
    3.7 Position encoding of words 46:02
    3.8 Summary 50:58
    *4. Unsupervised and transfer learning with BERT **54:45*
    4.1 Problems in language 55:39
    4.2 BERT 59:42
    -Unsupervised learning
    --Masked language model pertaining 1:02:05
    --Next sentence prediction pertaining 1:05:55
    -BERT fine-tuning 1:09:55
    -BERT supercharges transfer learning 1:12:05
    *7. Extract language-related knowledge from the environment **1:13:55*
    -Grounded language learning at DeepMind: towards language understanding in a situated agent
    *8. To conclude **1:27:18*

  • @prakhyatshankesi3749
    @prakhyatshankesi3749 Рік тому +1

    This is hands down, The best explanation of Transformers!

    • @antonioskarvelas1325
      @antonioskarvelas1325 6 місяців тому

      Best explanation? Unfortunately, it was difficult for me to follow ...

  • @martinho1688
    @martinho1688 4 роки тому +4

    Thank you very much for taking the time to prepare this incredible lecture series! #respectfrombrazil 🇧🇷

  • @luksdoc
    @luksdoc 4 роки тому +1

    One of the best lectures in the series.

  • @kirillazhitsky9842
    @kirillazhitsky9842 4 роки тому

    It's really informative, thank you. There is only one noticeable failure - it is not a fruit fly on the picture :)

  • @iamjameswong
    @iamjameswong 4 роки тому +4

    Thanks Felix! You're a great teacher. That's it.

  • @khadijakhaldi6468
    @khadijakhaldi6468 4 роки тому +4

    Thank you so much for the very informative lecture!

  • @6452gaurav
    @6452gaurav 4 роки тому +2

    Looks like Linus Sebastian is taking the lecture :D

  • @lukn4100
    @lukn4100 3 роки тому +1

    Great lecture and big thanks to DeepMind for sharing this great content.

  • @seremetvlad
    @seremetvlad 4 роки тому +2

    Thank you! This is a great series of lectures!

  • @lukn4100
    @lukn4100 3 роки тому +2

    Is the picture at 37:12 correct? Because, if we take a small amout of the value of each of the other words, plus the value of the word "beetle" to the next layer, then for me the v term from the word "the" should be connected to lambda1 and not the v term for the word "beetle". The same logic should be applied to the other words and their lambdas.

    • @gwendallevaillant9637
      @gwendallevaillant9637 3 роки тому

      I agree, there seems to be an issue with arrows in that figure. As the lambdas sum to 1, if the figure was right then v' would be equal to v_beetle.

  • @markusbuchholz3518
    @markusbuchholz3518 4 роки тому

    Impressive effort has been done in preparation regarding lecture. Thanks for sharing the knowledge and research.

  • @fgh509
    @fgh509 4 роки тому +2

    Amazing explanation of the Transformer, thanks so much

  • @abdurrezzakefe5308
    @abdurrezzakefe5308 3 роки тому

    I got Covid from 15:28 lol
    Great lectures btw, huge thanks to DeepMind and UCL!

  • @YeTianlinguist
    @YeTianlinguist 4 роки тому

    Thank you for the amazing lecture. Why are there only feedforward, but not feedback mechanisms in language models? Would that make a difference? We process language both bottom up and top down. Our expectation of the world, our beliefs of people's intentions can influence how we process a sequence of sound, just like how topdown processes make us hallucinate certain aspects of vision. The skip level connections allow lower down information to feedback up, but does not allow higher level representations to influence representation lower down, at least not at inference time. Would it be possible to have such a structure in Transformers? Would it help?

  • @bryanbosire
    @bryanbosire 3 роки тому

    Superb Lecture...Thank you

  • @JuanPabloBragaBrum
    @JuanPabloBragaBrum 4 роки тому +1

    Thanks for sharing knowledge!!

  • @pariveshplayson
    @pariveshplayson 2 роки тому

    Amazing lecture!

  • @user-or7ji5hv8y
    @user-or7ji5hv8y 4 роки тому +6

    Not easy to follow the exact steps with the visualization and explanation provided. I think more detail would be helpful.

    • @lukn4100
      @lukn4100 3 роки тому +4

      The explanations by the lecturer are great but the slides do not reflect this. They are too poor.

  • @ながれる季節
    @ながれる季節 3 роки тому +1

    I'm completely lost. Is this a graduate level course?

  •  4 роки тому +2

    1:27:57 "We've reached the end of the lecture, because I urgently need to go now…"

  • @fabb802
    @fabb802 Рік тому

    Thanks!

  • @wy2528
    @wy2528 4 роки тому

    Thank you for sharing the research.

  • @cuenta4384
    @cuenta4384 3 роки тому

    can anybody post the paper at the end where it says McClelland et 2019

  • @prizmaweb
    @prizmaweb 4 роки тому

    Excellent,.

  • @ragulshan6490
    @ragulshan6490 4 роки тому

    Thank you for for this amazing tutorial. Well organised!!

  • @a.gmathiu7995
    @a.gmathiu7995 3 роки тому

    Head of search

  • @firstnamesecondname5341
    @firstnamesecondname5341 4 роки тому

    He who is first shall be last, or just seen of as a twat 😁🤦🏻‍♂️🤣👍

  • @JigawattMusic
    @JigawattMusic 4 роки тому

    FIRST