DeepMind x UCL | Deep Learning Lectures | 8/12 | Attention and Memory in Deep Learning

Поділитися
Вставка
  • Опубліковано 20 лис 2024

КОМЕНТАРІ • 46

  • @kimchi_taco
    @kimchi_taco Рік тому +4

    Alex Graves invented CTC and RNNT, which is basically a modern e2e ASR model in 2013. It created tens of thousands of research jobs, and he left to seek his desire. His journey is inspiring. He doesn't seek fame or money or status. He seeks the answer to his internal curiosity. I wanna live like him.

  • @leixun
    @leixun 4 роки тому +44

    *DeepMind x UCL | Deep Learning Lectures | 8/12 | Attention and Memory in Deep Learning*
    *My takeaways:*
    *1. Introduction **1:24*
    1.1 Attention, memory and cognition 1:28
    1.2 Attention in neural networks 2:50
    -Implicit
    -Can be checked through Jacobian
    1.3 Explicit attention: hard attention, non-differentiable 17:00
    -It has several advantages over implicit attention
    --Computational efficiency
    --Scalability (e.g. fixed size glimpse for any size image)
    --Sequential processing of static data (e.g. moving gaze)
    --Easier to interpret
    -Neural attention models 19:24
    -Glimpse distribution 20:25
    -Attention with reinforcement learning 21:12
    -Complex glimpse 22:46
    *2. Explicit attention: soft attention, differentiable **26:27*
    2.1 Basic 28:15
    2.2 Attention weights 29:22
    2.3 An example: handwriting synthesis with RNNs 32:40
    2.4 Associative attention 38:38
    2.5 Differentiable visual attention 45:30
    *3. Introspective attention **49:23*
    3.1 Neural Turing Machine 51:02
    3.2 Selective attention 52:53
    3.3 Content-based and location-based attention 55:28
    3.4 Differentiable Neural Computer 1:12:04
    *4. Further topics **1:13:51*
    4.1 Self-attention in Transformers 1:14:00
    *5. Summary **1:34:14*

    • @softerseltzer
      @softerseltzer 4 роки тому

      22:25 : I'm checking all my tabs for notifications

    • @leixun
      @leixun 3 роки тому +1

      @jawad mansoor You’re welcome

  • @drpchankh
    @drpchankh 4 роки тому +8

    A no-nonsense detailed attention based lectures. A very well prepared lecture for all (beginners and experienced deep learning practitioner). Greatly recommended for all who want a context on how attention is first thought through in the research world. Thank you Alex. Enjoyed the lecture.

  • @menesun
    @menesun 2 роки тому +9

    From comment of Lei Xun (I added a 0.00 timestamp for the see chapters in the video)
    0. Opening 0:00
    1. Introduction 1:24
    1.1 Attention, memory and cognition 1:28
    1.2 Attention in neural networks 2:50
    -Implicit
    -Can be checked through Jacobian
    1.3 Explicit attention: hard attention, non-differentiable 17:00
    -It has several advantages over implicit attention
    --Computational efficiency
    --Scalability (e.g. fixed size glimpse for any size image)
    --Sequential processing of static data (e.g. moving gaze)
    --Easier to interpret
    -Neural attention models 19:24
    -Glimpse distribution 20:25
    -Attention with reinforcement learning 21:12
    -Complex glimpse 22:46
    2. Explicit attention: soft attention, differentiable 26:27
    2.1 Basic 28:15
    2.2 Attention weights 29:22
    2.3 An example: handwriting synthesis with RNNs 32:40
    2.4 Associative attention 38:38
    2.5 Differentiable visual attention 45:30
    3. Introspective attention 49:23
    3.1 Neural Turing Machine 51:02
    3.2 Selective attention 52:53
    3.3 Content-based and location-based attention 55:28
    3.4 Differentiable Neural Computer 1:12:04
    4. Further topics 1:13:51
    4.1 Self-attention in Transformers 1:14:00
    5. Summary 1:34:14

  • @stephennfernandes
    @stephennfernandes 4 роки тому

    Great Lecture ! Highly recommend anyone who is looking for indepth understanding of attention and different families of attention mechanism please watch this video . Its the best attention explanation available on the entire web.

  • @barisdenizsaglam
    @barisdenizsaglam 4 роки тому +11

    Great lecture! I really appreciate how he explains the thought process behind the new ideas.

  • @peterdavidfagan
    @peterdavidfagan 2 роки тому

    This is one of my all-time favorite lectures, thanks for making this available. DNCs are very interesting.

  • @pw7225
    @pw7225 2 роки тому +1

    This is sooooooo good. So well explained. It's like a Neuralink knowledge upload to my brain. Thanks, Alex!

  • @agamemnonc
    @agamemnonc Рік тому

    I like the "Thank you very much for your attention" punch line at the end.

  • @Naghaas
    @Naghaas 11 місяців тому

    Another high quality course from deepmind, thanks !

  • @Letsfeelthenaturee
    @Letsfeelthenaturee 4 роки тому

    You are really brilliant, sir. I am from your friend country Bangladesh 🇧🇩. Hope you will be more and more helpful

  • @BlackHermit
    @BlackHermit 4 роки тому +1

    This is only the beginning.

  • @ansh6848
    @ansh6848 2 роки тому

    Looking for a lecture on attention mechanism..and This was the best.

  • @quentinpaden1481
    @quentinpaden1481 8 місяців тому +1

    Revive UA-cam

  • @lukn4100
    @lukn4100 3 роки тому +1

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

  • @marcelomanteigas
    @marcelomanteigas 4 роки тому +4

    wonderful! Thanks for putting these lectures out!!

  • @ProfessionalTycoons
    @ProfessionalTycoons 4 роки тому +1

    thank you for this lecture, learned a lot about attention

  • @robertfoertsch
    @robertfoertsch 4 роки тому +1

    Excellent, Added To My Research Library, Sharing Through TheTRUTH Network...

  • @GrigorySapunov
    @GrigorySapunov 4 роки тому

    Thanks Alex for the cool lecture and research!

  • @kaymengjialyu5086
    @kaymengjialyu5086 4 роки тому +1

    Dear DeepMind, the link for the slides seems to be valid. Can anyone fix that?

  • @stanislavjirak2894
    @stanislavjirak2894 Рік тому

    Splendid!! 🎉

  • @PresidentGollumSmeag
    @PresidentGollumSmeag 10 місяців тому +3

    hey! i really enjoyed the machine lecturing! BUT!!!! your name is graves but i dont see a scar and i played u quite a bit in aram and also no cigar and also no shotgun and also no collector in ur item list in the background! PROPS FOR THE BEARD!!! FRAUD!!!!!!!

    • @Adrixin
      @Adrixin 10 місяців тому

      totally agree. needless to say he was camping base the entire time afk

  • @siyn007
    @siyn007 4 роки тому

    For anyone that watched this lecture and his lecture from two years ago, is the difference large enough for me to watch the one from two years ago? Thanks

    • @mabbasiazad
      @mabbasiazad 4 роки тому +2

      The section discussed after 1:14:00 (Further topic) is new.

    • @siyn007
      @siyn007 4 роки тому +1

      @@mabbasiazad thanks!

  • @AnonymousIguana
    @AnonymousIguana Рік тому

    Fantastic :)

  • @YaroslavVolovich
    @YaroslavVolovich 4 роки тому

    Thanks Alex for a great lecture!

  • @rogerab1792
    @rogerab1792 4 роки тому

    Memmory Augmented Neural Networks are the next big thing.

  • @hosseinsheikhi5596
    @hosseinsheikhi5596 4 роки тому

    Amazing lecture!

  • @pratik245
    @pratik245 2 роки тому

    These things seem eeringly similar to an idea i had 5 years ago and wrote some innocuous linkedin article around tge same same transformers delved into attnetion mechanism. But, only those who actually are in Harvard, MIT, deep mind can actually implement it with the resources that are required for it.

    • @robensonlarokulu4963
      @robensonlarokulu4963 Рік тому

      No worries! Jürgen Schmidhuber already invented all those stuff and all relevant ideas at least 30-40 years ago. Maybe earlier, just around while he was a suckling infant.

    • @pratik245
      @pratik245 Рік тому

      @@robensonlarokulu4963 yeah.. Also true that losers will be losers right from the time they are born.

    • @pratik245
      @pratik245 Рік тому

      Also, understand the difference between me and you, i never want credit for anything but i don't like stealing. Do you know who rudra is, that is what i become when i see too much injustice.. So better stay away from sucking any future generation's blood. If i see such injustice, believe me you will know God's wrath..

  • @amniasalma307
    @amniasalma307 4 роки тому

    Thanks for sharing this

  • @priancho
    @priancho 4 роки тому +1

    Thank you for such a good lecture! :=)

  • @deeplearningpartnership
    @deeplearningpartnership 4 роки тому

    Amazing.

  • @quentinpaden1481
    @quentinpaden1481 8 місяців тому +1

    Police UA-cam

  •  4 роки тому

    "Attention is all you need"? What a missed opportunity to call the paper "Give me some attention and I'll do everything you want". ;)