Transfer learning and Transformer models (ML Tech Talks)

แชร์
ฝัง
  • เผยแพร่เมื่อ 10 พ.ย. 2024

ความคิดเห็น • 87

  • @klammer75
    @klammer75 3 ปีที่แล้ว +100

    This was one of the best videos I’ve seen explaining transformers and NL models….well done and look forward to the other videos in the series!🍻

  • @maudentable
    @maudentable ปีที่แล้ว

    This is the best video on youtube that introduces transformer models

  • @timoose3960
    @timoose3960 3 ปีที่แล้ว +3

    The comparison between attentions heads and CNN filters made so much sense!

  • @paygood
    @paygood ปีที่แล้ว

    I believe this video provides the most comprehensive explanation of transformers.

  • @miladchenaghlou5278
    @miladchenaghlou5278 2 ปีที่แล้ว +1

    After reading about language models, word embeddings, transformers, etc. for a month, this video put everything in order for me. Thanks!

    • @strongsyedaa7378
      @strongsyedaa7378 2 ปีที่แล้ว +1

      I didn't understand a single word 😕

  • @BiswajitGhosh-wg6qj
    @BiswajitGhosh-wg6qj 3 ปีที่แล้ว +10

    Please @Tensorflow Team continue with this lecture series ML Tech series

  • @harryz7973
    @harryz7973 2 ปีที่แล้ว +1

    best youtube NLP walk through without cutting corners. best delivery as well.

  • @kanikaagarwal6150
    @kanikaagarwal6150 2 ปีที่แล้ว +1

    One of the best explanation i have come across on transformers. Thanks

  • @ArtificialWisdomCloud
    @ArtificialWisdomCloud ปีที่แล้ว +1

    Mapping to geometry is pro. I have thought since my education about 40 years ago that current mathematics is taught incorrectly. Here is a pro example of how math should be taught!

  • @jorgegines1802
    @jorgegines1802 ปีที่แล้ว +3

    A cristal clear explanation of Transformers. Papers in many cases are very difficult to follow. Pointing out the important omited details which are critical for the model, even if not explained, is very useful. Many out there try to explain transformers without having a clue of what it is. Clearly, this is not the case. Thanks in its deepest tokenized meaning for sharing your knowledge. BTW, the last programming tip is really helpful. A small hands on demo of using BERT(or any flavor of BERT) with a classifier for a particular application would be amazing for another video.

  • @correctmeifiamwrong5862
    @correctmeifiamwrong5862 2 ปีที่แล้ว +1

    Great Video. The first Transformer explanation that (correctly) does not use the Encoder/Decoder diagram from the Transformer paper, well done!
    Additionally talking about the exact outputs (using only one output for predictions) was very helpful.

  • @JTedam
    @JTedam ปีที่แล้ว

    So clear. This is one of the best videos explaining transformer architecture.

  • @sergiobdbd
    @sergiobdbd 2 ปีที่แล้ว

    One of the best explanations of transformers that I've seen!

  • @goelnikhils
    @goelnikhils ปีที่แล้ว

    Best Video on Transfer Learning. So much clarity

  • @inteligenciamilgrau
    @inteligenciamilgrau 6 หลายเดือนก่อน

    After a year returning to that video finally I fully (or at least saw the entire video in a row) understand what is going on!! Maybe one more time to fix and go to the next part!! Thanxx

  • @OtRatsaphong
    @OtRatsaphong 2 ปีที่แล้ว +3

    Great overview and explanation of the Transformer network. I am just starting my exploration into NLP and this talk has saved me lots of time. I now know that this where I need to be focussing my attention. Thank you 👍🙏😍

  • @moseswai-mingwong8307
    @moseswai-mingwong8307 3 ปีที่แล้ว +3

    Thank you for the awesome talk on all the main NLP models, in particular, the great explanation of the Transformer model!

  • @shivibhatia1613
    @shivibhatia1613 11 หลายเดือนก่อน

    Hands down the best explanation, this after watching so many videos, terrific, Looking forward to some videos on understanding on BARD and its fine tuning

  • @irfanyaqub9643
    @irfanyaqub9643 ปีที่แล้ว

    She has done an incredible job.

  • @GBlunted
    @GBlunted 2 ปีที่แล้ว +9

    She's so good! I've watched a few videos attempting to explain these self-attention version of transformers and this one is by far the best in so many aspects with actual deep understanding of the architecture at the top followed closely by coherently communicating concepts, good script, presentation and graphics! I hope she narrates more videos like this... I'm about to search and find out lol! 🧐🤞 🤓

  • @jocalvo
    @jocalvo 2 ปีที่แล้ว

    Wow that explanation actually dissipated many of my questions. Thanks a lot Julia!

  • @josephpareti9156
    @josephpareti9156 2 ปีที่แล้ว

    awesome; the very BEST explanation on self-attention and trasformers

  • @user-wr4yl7tx3w
    @user-wr4yl7tx3w 2 ปีที่แล้ว

    My favorite explanation so far. Great job.

  • @karanacharya18
    @karanacharya18 ปีที่แล้ว

    Very well explained! Thank you very much. Especially loved the comparison between CV kernels and multiple QKV parameters.

  • @PaulFishwick
    @PaulFishwick 3 ปีที่แล้ว

    Agreed with all. This person should take the lead for other Google educational videos.

  • @toplizard
    @toplizard 10 หลายเดือนก่อน

    This is very beautifully explained!

  • @deepaksadulla8974
    @deepaksadulla8974 3 ปีที่แล้ว +1

    Best explanations so far of the attention or QKV concept... I was searching for a good way to visualize it.. Thanks a ton!!

  • @aikw5946
    @aikw5946 ปีที่แล้ว

    Thank you very much ! Great video and very well explained. Yes a video about sentiment analysisfine tuning would be Amazing !

  • @Vinicius-nd8nz
    @Vinicius-nd8nz ปีที่แล้ว

    Great presentation! Really easy to understand exaplanations of some hard topics, thank you.

  • @Jacob011
    @Jacob011 3 ปีที่แล้ว +1

    I expected some wishy-washy feel-good "explanation", but I'm pleasantly surprised. So far the best explanation. Goes after the relevant distinguishing key features of the transformers without getting bogged down in unnecessary details.

  • @jacobyoung2045
    @jacobyoung2045 3 ปีที่แล้ว +3

    44:40: Thanks for your attention 😁

  • @WARATEL_114_30
    @WARATEL_114_30 3 ปีที่แล้ว +2

    Very straightforward.
    Thank you so much

  • @user-or7ji5hv8y
    @user-or7ji5hv8y 3 ปีที่แล้ว +2

    Great presentation. Really well structured.

  • @zedudli
    @zedudli ปีที่แล้ว

    That was super interesting. Very clear explanation

  • @gunnarw97
    @gunnarw97 ปีที่แล้ว +1

    Great explanations, thank you so much for this video!

    • @TensorFlow
      @TensorFlow  ปีที่แล้ว

      Glad it was helpful!

  • @geshi7121
    @geshi7121 3 ปีที่แล้ว +1

    The explanation is so clear, thank you.

  • @jvishnuiitm123
    @jvishnuiitm123 2 ปีที่แล้ว

    Excellent presentation of complex NLP topic.

  • @PavelTverdunov
    @PavelTverdunov 2 ปีที่แล้ว

    super professional explanation of the topic! Excellent work!

  • @EngRiadAlmadani
    @EngRiadAlmadani 3 ปีที่แล้ว +1

    It's very important library in nlp great work

  • @JTedam
    @JTedam ปีที่แล้ว

    Julia,
    Your presentation has triggered a Eureka moment in me . What makes a great training video? Can AI help answer that. Here is a suggestion. Get a collection of videos and rank them by review comments. Using a large language model, find patterns and features and see whether there are correlations between the features and the views and review rankings. The model should be unsupervised. Some of the features can be extracted from comments

  • @davidobembe5302
    @davidobembe5302 3 ปีที่แล้ว +2

    Very clear explanation. Thank youuu

  • @jimnason7293
    @jimnason7293 ปีที่แล้ว

    Very nice topic discussion! Thank you 🙂

  • @FinnBrownc
    @FinnBrownc 2 ปีที่แล้ว

    This is a positive comment. TH-cam should let it past it’s sentiment filter.

  • @bryanbosire
    @bryanbosire 3 ปีที่แล้ว +1

    Great Presentation

  • @santhoshkrishnan6269
    @santhoshkrishnan6269 ปีที่แล้ว

    Great Explanation

  • @ThomasYangLi
    @ThomasYangLi ปีที่แล้ว

    very good presentation!

  • @Randomize-md3bt
    @Randomize-md3bt ปีที่แล้ว

    I came here from tutorials sections of tensorflow official webpage, but i get caught by her beauty

  • @rwp8033
    @rwp8033 3 ปีที่แล้ว

    Great video, it would be nice to have a video of reinforcement learning in future ml tech talks.

  • @赵玥-e9q
    @赵玥-e9q ปีที่แล้ว +1

    well done video!

  • @ManzoorAliRA
    @ManzoorAliRA ปีที่แล้ว

    Simply awesome

  • @parsarahimi71
    @parsarahimi71 3 ปีที่แล้ว +1

    Crystal clear .. Tnx

  • @davedurbin813
    @davedurbin813 2 ปีที่แล้ว

    Great talk, really clear, thanks!
    Also I see what you did "Thanks for your attention" 🤣

  • @pohkeamtan9876
    @pohkeamtan9876 3 ปีที่แล้ว

    Excellent teaching !

  • @devanshbatra5267
    @devanshbatra5267 ปีที่แล้ว

    Thanks a ton for the explantion! Just wanted to ask how do we arrive at the values for matrices K, V and Q?

  • @SanataniAryavrat
    @SanataniAryavrat 3 ปีที่แล้ว +1

    Awesome.. great explanation. Thanks.

  • @jantuitman
    @jantuitman 2 ปีที่แล้ว

    This is a fairly good presentation. There are some areas where it summarizes to the point where it becomes almost misleading, and at least very questionable: 1. Several other sources that I read claim that the Bert layers will have to be frozen during fine tuning, so I think it is still open for debate what the right thing to do is there? 2. This presentation glosses over the outputs of the pretraining phase. I think the output corresponding to the CLS token is pretrained with the “next sentence prediction task”. So, is this output layer dropped entirely in the fine tuning task? Otherwise I don’t see how the CLS token output would be a good input for sentiment classification. 3. The presentation suggest that the initial non contextual token step is also trainable and fine tunable. Isn’t it just fixed byte pair encodings? I know that these depend on frequencies of letters in the language but can these be trained in process with Bert? 4. This presentation equals transformers very silently to transformer encoders, and thus drops the fact that transformers can also be decoders. I think all initial transformers were trained on sequence to sequence transformation, and then the decoders were trained on next token prediction giving rise to things like GPT, whereas the encoders were trained on a combination of masked token prediction and next sentence prediction giving rise to the BERT like models.

  • @haneulkim4902
    @haneulkim4902 2 ปีที่แล้ว

    Amazing talk! very informative. Thank you :)

  • @herbertk9266
    @herbertk9266 3 ปีที่แล้ว +2

    Thank you

  • @FarisSkt
    @FarisSkt 3 ปีที่แล้ว +1

    amazing video !

  • @sanjaybhatikar
    @sanjaybhatikar ปีที่แล้ว

    Nice, thank you ❤

  • @josephpareti9156
    @josephpareti9156 2 ปีที่แล้ว

    at minute 35 the video describes transfer learning, and it is said that during the fine tuning phase ALL the parameters are adjusted, not only the classifier parameters. Is that right? In contrast, when using a pre-trained deep network for a specific image calssification, I froze all parameters belonging to the CNN and just allowed the classifier parameters to vary

  • @OnionKnight541
    @OnionKnight541 ปีที่แล้ว +1

    very nice

  • @lbognini
    @lbognini 3 ปีที่แล้ว

    Simply great! 👏👏👏

  • @amitjain9389
    @amitjain9389 ปีที่แล้ว

    Where can I get the slides for this talk? Great talk

  • @satyajit1512
    @satyajit1512 3 ปีที่แล้ว

    Great slides.

  • @saurabhkumar-yf1vs
    @saurabhkumar-yf1vs 2 ปีที่แล้ว

    real help, thanks.

  • @joekakone
    @joekakone 3 ปีที่แล้ว +1

    Thank you for shraing !

  • @fahemhamou6170
    @fahemhamou6170 2 ปีที่แล้ว

    تحياتي الخالصة شكرا جزيلا

  • @chavdarpapazov4423
    @chavdarpapazov4423 3 ปีที่แล้ว +3

    Great presentation! Are the slides available for download? This would be fantastic. Thank you.

  • @vunguyenthai4366
    @vunguyenthai4366 3 ปีที่แล้ว

    nice video

  • @arnablaha
    @arnablaha 6 หลายเดือนก่อน

    Immaculate!

  • @billyblackburn864
    @billyblackburn864 ปีที่แล้ว

    i love it

  • @koushikroy6259
    @koushikroy6259 2 ปีที่แล้ว

    Thanks for your ATTENTION 🤗🤗.. Pun intended!44:39

  • @shakilkhan4306
    @shakilkhan4306 ปีที่แล้ว +1

    Interesting

  • @jdcrunchman999
    @jdcrunchman999 ปีที่แล้ว

    Where can I get the GitHub file

  • @it-series-music
    @it-series-music 2 ปีที่แล้ว

    Can someone explain the inputs dict shown in the code at 42:15.

  • @ravipratapmishra7013
    @ravipratapmishra7013 2 ปีที่แล้ว

    Please provide the slides

  • @enes-the-cat-father
    @enes-the-cat-father 3 ปีที่แล้ว

    Thanks for not calling Sentiment Classification as Sentiment Analysis!

  • @alikhatami6610
    @alikhatami6610 2 ปีที่แล้ว

    okay what you are saying is completely vague . like for the query matrice you mentioned ( some other representation [why do we need another representation at all ?])

  • @babaka1850
    @babaka1850 6 หลายเดือนก่อน

    Sorry to say, but this was not very good. Key information is missing mostly the WHYs ? why is there a need for Query and Key Matrices? what is the main function of these matrices? How does the Attention function alter the Feedforward NNs?

  • @algogirl2846
    @algogirl2846 3 ปีที่แล้ว

    👍🏻👍🏻👌

  • @mohammadmousavi1
    @mohammadmousavi1 2 ปีที่แล้ว

    I always find the face of presenter distracting when it is on the slides … can you just talk over slides instead of covering them with presenter’s face??