What does it mean for computers to understand language? | LM1

Поделиться
HTML-код
  • Опубликовано: 26 дек 2024

Комментарии • 75

  • @vcubingx
    @vcubingx  8 месяцев назад +23

    If you enjoyed the video, please consider subscribing :)
    Part 2: ruclips.net/video/rTz6hadM1Lg/видео.html
    I'm excited to be starting this new series! NLP is the topic I feel like I have the most to say about, but I'll avoid throwing in my personal opinions into these videos :p Stay tuned for the next chapter which I'll be posting next Monday!! (And the third chapter next to next week). Also, let me know what other kinds of topics you'd be interested in seeing!!!

    • @sethdon1100
      @sethdon1100 8 месяцев назад +1

      Strange timing you go there…
      3B1B published basically the same video before you.

    • @yjp20
      @yjp20 8 месяцев назад

      The 🐐

    • @1XxDoubleshotxX1
      @1XxDoubleshotxX1 8 месяцев назад

      so hot

    • @buddhadevbhattacharjee1363
      @buddhadevbhattacharjee1363 8 месяцев назад +1

      Hi, One of the topics which I am struggling with understanding is the requirement of V in QKV and why the multihead attention outputs are concatenated rather than doing any other operation.If you could make a video on concatenation of vectors and how they retain information better that would be great

    • @vcubingx
      @vcubingx  8 месяцев назад

      @@buddhadevbhattacharjee1363 hmmm, interesting question for sure! I believe the reason concatenation is done is just because its loss-less (retains all information).This is just a standard DL practice - for example, we concatenate the positional embeddings too.
      The next to next chapter will be on attention. Let me know if that addresses you questions, and if not, I'll look into what a follow-up video could contain.
      Thanks ofr your input!

  • @johndewey7243
    @johndewey7243 8 месяцев назад +5

    Just came from 3B1B, subbed this is excellent. Thanks!

  • @PiercingSight
    @PiercingSight 8 месяцев назад +16

    What timing for this video~
    Looking forward to more!

    • @vcubingx
      @vcubingx  8 месяцев назад +2

      Thanks!!

  • @miss-magic-maya
    @miss-magic-maya 8 месяцев назад +3

    This is wonderful, excited for the next video!
    Also nice choice of music :)

    • @vcubingx
      @vcubingx  8 месяцев назад

      Thanks! Love nintendo music :)

  • @ianthehunter3532
    @ianthehunter3532 8 месяцев назад +81

    Odd timing 🤔

    • @jujdj6214
      @jujdj6214 8 месяцев назад +2

      ye.

    • @vcubingx
      @vcubingx  8 месяцев назад +8

      Indeed, haha!

  • @chineduezeofor2481
    @chineduezeofor2481 7 месяцев назад +1

    Found this by watching 3Blue1Brown
    Awesome channel!

  • @dattatreyadas
    @dattatreyadas 8 месяцев назад +4

    10:14 Brought to you by... 3Blue1Brown!!

  • @cyanurecyanures130
    @cyanurecyanures130 6 месяцев назад +1

    Thanks a lot for the video ! Now I understood that Trigrams model just take into acount the last three words.

  • @averagemilffan
    @averagemilffan 8 месяцев назад +2

    Great video!! I'm hoping you discuss some of the history in the next episodes too though

    • @1XxDoubleshotxX1
      @1XxDoubleshotxX1 8 месяцев назад

      agree!

    • @vcubingx
      @vcubingx  8 месяцев назад +1

      That's the plan! I'm trying to touch on key papers until 2016

  • @artahir123
    @artahir123 8 месяцев назад +3

    brother never stop making these videos
    these are very interesting

    • @vcubingx
      @vcubingx  8 месяцев назад +1

      Glad you like them!

  • @davidespinosa1910
    @davidespinosa1910 3 месяца назад +1

    Just for general interest, here are a few examples of syntax vs semantics. Consider "The tree ate a banana". It's syntactically valid, but it doesn't mean anything. Or, "Is a dog conscious ?". It's also syntactically valid, but it doesn't mean anything until we decide what "conscious" means. Or, "Does the past still exist ?". It doesn't mean anything until we decide what "exist" means.

  • @MrWater2
    @MrWater2 8 месяцев назад

    Good one! I'll be waiting for the next one

    • @vcubingx
      @vcubingx  8 месяцев назад

      Thanks! Currently working on it - should be up on Monday

  • @imtanuki4106
    @imtanuki4106 2 месяца назад

    Nicely done!

  • @Randomstiontastic
    @Randomstiontastic 8 месяцев назад +34

    You uploaded this a minute after 3b1b’s video, how?

    • @Orillians
      @Orillians 8 месяцев назад +6

      IKR. FIRST I WAS WONDERING HOW AND THEN THIS TOO WHAT WHAT

    • @cwaddle
      @cwaddle 8 месяцев назад +1

      This dude must be 3b1bs younger bro, or a buddy

    • @laycookie-f6i
      @laycookie-f6i 8 месяцев назад

      I was like when did 3b1b release the video about transformers? Turns out same time as this video

    • @vcubingx
      @vcubingx  8 месяцев назад +8

      :)

    • @laycookie-f6i
      @laycookie-f6i 8 месяцев назад

      @@vcubingx What a troll.

  • @jamesking2439
    @jamesking2439 8 месяцев назад +8

    We're eating good today guys.

  • @PastisPastek
    @PastisPastek 8 месяцев назад +1

    Perfect timing

  • @amirjutt0
    @amirjutt0 8 месяцев назад

    You'll go up boi. Just put in the effort. Make the quality content. People are looking for quality content related to ML.

  • @mihairobert-catalin951
    @mihairobert-catalin951 Месяц назад

    What's the module of |V| , what it represents in the context?

  • @stellastaraj
    @stellastaraj 7 месяцев назад

    Hi, love the video - just one thing, the C in the Probability equation throws me off. I keep reading it in my mind as "complement" - as in the complement of a set. I'm probably missing the right context for it. I can grasp from what you're saying that it probably signifies occurrences of the event, but uncertain why it's "c". Is it c for condition ?

    • @vcubingx
      @vcubingx  7 месяцев назад

      C stands for count. Sorry! It can be a bit confusing - should’ve explained it. Some of the notation NLP folk use is certainly questionable

  • @gwonchanjasonyoon8087
    @gwonchanjasonyoon8087 5 месяцев назад

    From 3b1b!

  • @calix-tang
    @calix-tang 8 месяцев назад

    mfv what a great job you have done

  • @alexeypankov8180
    @alexeypankov8180 8 месяцев назад

    great vid frfr

  • @tomoki-v6o
    @tomoki-v6o 8 месяцев назад +1

    Still waiting for part 3 on neural networks

    • @vcubingx
      @vcubingx  8 месяцев назад +6

      Dang, it's been 4 years already...how time flies by.
      I'll try and make this my next-to-next-to-next video (After Chapter 3 of this series). Sorry for the delay, and I'm happy you're still around to wait for it :)

  • @rohitkavuluru8998
    @rohitkavuluru8998 8 месяцев назад

    Goated

  • @AnmolSharma-ij1ut
    @AnmolSharma-ij1ut 8 месяцев назад

    Dame bro it was too good i don't know about g gram

  • @tolgaerdonmez3574
    @tolgaerdonmez3574 Месяц назад

    its awesome, please remove the background music, very distracting :(

  • @skifast_takechances
    @skifast_takechances 8 месяцев назад

    bro is basically alan turing at this point

    • @vcubingx
      @vcubingx  8 месяцев назад

      ski fast take chances

  • @ucngominh3354
    @ucngominh3354 8 месяцев назад +1

    hi

  • @YoussefMohamed-er6zy
    @YoussefMohamed-er6zy 8 месяцев назад +1

    you know what chatgpt is unfortunately, the manifestation of the Chinese room paradox, and it is SO humorous that we are taking that much time to realize

    • @Iknowwereyousleep289
      @Iknowwereyousleep289 8 месяцев назад

      You’re stupid:
      The Chinese room argument doesn't work for complex tasks beyond fixed rule-based symbolic manipulation. AI like ChatGPT goes beyond counting word co-occurrences, making decisions based on intricate feature interactions. We need to clearly define "understanding" first.
      Understanding involves making functional predictions by compressing data into representations in vector space synaptic interactions etc. GPT-4 doesn’t store explicit symbols but extracts features from data, comprehending context rather than concrete content. Fixed translation are without representational ability to demonstrate understanding.

  • @dannysunginpark7561
    @dannysunginpark7561 8 месяцев назад

    breh

    • @vcubingx
      @vcubingx  8 месяцев назад

      dang retired cuber comes out of the dead only to smash mohanraj's 3x3x3 PR average

  • @1XxDoubleshotxX1
    @1XxDoubleshotxX1 8 месяцев назад +1

    you should make a video on how to get girls

  • @blankboy-ww7jt
    @blankboy-ww7jt 8 месяцев назад

    Third

  • @Dhruvbala
    @Dhruvbala 9 месяцев назад

    First

  • @fintech1378
    @fintech1378 8 месяцев назад

    This is so Asian

  • @OBGynKenobi
    @OBGynKenobi 8 месяцев назад

    Computers "understand" languages in as far as they can compute statistics. But they don't really understand like humans do. For example can they understand the levels of meaning of poetry, or sarcasm, or cynicism?

    • @panulli4
      @panulli4 8 месяцев назад +8

      What makes you think that human brains don’t just compute statistics?

    • @aaronspeedy7780
      @aaronspeedy7780 8 месяцев назад

      @@panulli4 I think the difference is that LLMs compute statistics on words themselves, while humans "perform statistics" on lots of different inputs, and then transform whatever result it gets into language

    • @vcubingx
      @vcubingx  8 месяцев назад +7

      To be honest, it's really unclear what it even means to "understand" language. I'm fairly certain that we should be able to get to a sarcasm-detection level of humans within the next 10 years. See relevant work: scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=sarcasm+detection&btnG=&oq=sarcasm+detection
      I feel like 5 years ago, the idea of being able to generate code was unfathomable. Yet, here we are, and Github Copilot knows C++ syntax almost perfectly. Who's to say that everything in our brain is not a type matrix multiplication? We don't know :)

    • @JosephParker7
      @JosephParker7 8 месяцев назад

      @@panulli4 And that intuition may be a consequence of analogical thinking and overlooking the subtleties involved. Not that it's "wrong", but arguments such as "the brain is he brain is definitely like a stack of LSTMs", or "the brain is just a Markov chain" etc. has always existed and they've only focused on certain overlaps to construct a simplistic explanation.
      Sure, certain submodules of the brain may operate stochastically, but it's also evident that there are a lot of other architectural complexities involved that allows for agentic behavior, continuous learning, inferring priors from observations, meta-awareness and deliberate allocation of attention and cognitive resources, and adapting to highly chaotic and out-of-distribution environments and contexts to name a few. Qualia itself hasn't been fully explained or understood and it's unclear if it can be, however there are good reasons to think it's a crucial mechanism that allows for agentic models to operate consistently and develop a coherent world model. It's highly likely it wouldn't simply "emerge" from scaling up statistical models. And equivalently, it's easy to conceptualize why a statistical model can achieve a high level of mastery in specific domains which are already deterministic or statistical in nature, or can at least be brute-force computed and generalized for but a lot of things aren't. You can for example, give the impression that you understand quantum mechanics by simply paraphrasing scientific articles, especially if you can do so at scale and very efficiently.

    • @OBGynKenobi
      @OBGynKenobi 8 месяцев назад

      @vcubingx yes, I'm not saying it can't happen. I'm only saying that at this point it's not there and it may take a while with more tech. And when I say a while, I mean that in the most open sense.