Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM)

Поделиться
HTML-код
  • Опубликовано: 11 июн 2024
  • Part of the End-to-End Machine Learning School Course 193, How Neural Networks Work at e2eml.school/193
  • НаукаНаука

Комментарии • 466

  • @ssundaraju
    @ssundaraju 4 года назад +42

    Brandon has applied extraordinary skills in communicating the difficult (convoluted?) topic and concepts on LSTM, in simple and comprehensible language. The example on writing the "Children Text Book" brings out all of the major processes into sharp focus. I have learnt immensely. I will now be studying other videos by Brandon. Thanks a lot.

  • @Skydmig
    @Skydmig 7 лет назад +229

    Everyone give this man an upvote. This is great material.

    • @asteroidX
      @asteroidX 2 года назад +1

      An upvote doesn’t justify. Plus hit the subscribe button.

  • @Murphyalex
    @Murphyalex 6 лет назад +64

    It makes me want to make four more RUclips accounts just to give the video more likes. I've been staring at the network diagrams on blog posts for a few weeks now with no idea how to really read it. That simple walkthrough on the small example was just perfect.

  • @brettensor
    @brettensor 7 месяцев назад +3

    I really appreciate how you wait to the very end to discuss the math of RNNs. Your approach of leading with the intuition of RNNs rather than the math was super helpful for me. Thank you for your work!

  • @jordanlee1439
    @jordanlee1439 7 лет назад +57

    The pace and clarity of the lecture is really refreshing. Methodically stated complete sentences are always welcomed in my book.

  • @sqripter256
    @sqripter256 4 года назад +5

    Easily the most intuitive intro tutorial on RNN/LSTMs. Great work and thanks

  • @DreamWorker-jm5xn
    @DreamWorker-jm5xn 4 года назад +75

    Yes, this is the best LSTM video on RUclips. Today is 27th July 2019.

    • @dattatreyapujar4068
      @dattatreyapujar4068 3 года назад +1

      What is the day today?

    • @bode_fuceta
      @bode_fuceta 3 года назад +5

      27th July 2020 *(1 year later exactly)* ...Best video yet

  • @fuuman5
    @fuuman5 4 года назад +13

    Insane explanation. Just invested 26 minutes of my time perfectly.

  • @kerbyboy43
    @kerbyboy43 Год назад +1

    im a student major in data science from taiwan and i wanna say thank you, i got more to know about LSTM after watching ur video. Much appreciate sir!

    • @BrandonRohrer
      @BrandonRohrer  Год назад

      You are very welcome. Best of luck in your studies!

  • @Spudst3r
    @Spudst3r 6 лет назад +10

    Your videos are absolutely amazing. You are the first educator to make these complex topics truly accessible to the general coder without the privilege of getting to attend Stanford. Thank you so much. Everyone I've shared this to has just eaten it up as well.

    • @Neonb88
      @Neonb88 4 года назад +1

      I actually thought there was a fly on my screen. Kudos!

    • @StarAI24
      @StarAI24 3 года назад

      @@Neonb88 didnt see the fly until you mentioned it lol

  • @mannversteckter5631
    @mannversteckter5631 2 года назад +1

    The example with Writing story is very clear. Thank u!!

  • @011azr
    @011azr 6 лет назад +1

    You explain everything in a crisply crystal clear way. What a great teacher! :)

  • @tasteyfoood
    @tasteyfoood 4 года назад +6

    As someone who learns best through story and images, this has been incredibly helpful. Thank you!

  • @GEB-Loop
    @GEB-Loop 3 года назад +1

    The best explanation of RNN and LSTM that I have ever come across. Thanks for sharing!

  • @fgfanta
    @fgfanta 6 лет назад

    The most approachable introduction to LSTM I have found so far.

  • @tomforstmann9977
    @tomforstmann9977 3 года назад +1

    Kind of meta-ironic watching this with automated subtitles enabled.
    Really good video on the subject, much appreciated!

  • @huyhoang752
    @huyhoang752 6 лет назад

    The best introduction to RNN and LSTM on RUclips! Thank you, Brandon!

  • @aaryannakhat1842
    @aaryannakhat1842 3 года назад +1

    This is probably the best video on RNN and LSTM that I have come across!

  • @swethanaik7121
    @swethanaik7121 3 года назад +1

    A very clear and concise concept of LSTM. Had a hard time trying to understand LSTM until I fell upon this video. Thanks Brandon for this

    • @BrandonRohrer
      @BrandonRohrer  3 года назад

      Thanks Swetha! I'm happy it helped :)

  • @PradyumnSharma
    @PradyumnSharma 4 года назад +1

    Brilliant! Such lively, easy-to-understand explanation. Wish there were more teachers like you.

  • @rainbain5474
    @rainbain5474 4 года назад +1

    I have been getting into neural networks for a while now, and this is the best material I have seen.

  • @TheodorosKatsikis
    @TheodorosKatsikis 4 года назад +3

    This has to be the best LSTM explanation I have seen! Awesome work! THANK YOU for making this

  • @jackshaak
    @jackshaak 3 года назад +1

    Great introduction to LSTM. Thank you sir.

  • @georgiostsoukas7270
    @georgiostsoukas7270 2 года назад

    Just brilliant. Not only learned about LSTMs but also how to do a proper presentation.

  • @hessamjamalkhah9781
    @hessamjamalkhah9781 3 года назад +2

    Dude you nailed it, this simplicity on explaining such a complex concept shows how great you are and the depth of your knowledge on the subject. Thank you so much.

    • @BrandonRohrer
      @BrandonRohrer  3 года назад

      Thanks Hessam, that is a giant compliment. I'm glad it helped.

  • @Damodharanjay
    @Damodharanjay 6 лет назад +2

    Hands Down! The best LSTM video I have ever seen! Thank you!

  • @yysatoshi
    @yysatoshi 2 года назад +2

    Is it only me who has no idea of what this genius is talking about

    • @saint79209
      @saint79209 Месяц назад

      😂😂😂 good one

  • @DagarCoH
    @DagarCoH 6 лет назад +6

    I have seen a couple of videos on the topic, and yours is easily the best. I would have had no chance to understand the other ones, had I not watches this here first. Thanks a lot!

    • @ibrahimelkilani8508
      @ibrahimelkilani8508 5 лет назад

      Really. Other videos do explain in hard scientific way unlike this one

  • @hitashukanjani4430
    @hitashukanjani4430 4 года назад +1

    Best possible explanation of LSTM

  • @ashlife17
    @ashlife17 3 года назад +2

    Absolutely wonderful and simplified video explaining LSTM. Thanks a ton Brandon!

  • @jaydayyyy611
    @jaydayyyy611 4 года назад

    I have never seen this level of simple explanation of LSTM ever. Awesome..

  • @vijayakumar4804
    @vijayakumar4804 2 года назад +1

    Hey Thanks Bradon, Complexity put forth in Layman's language, just loved it!!!

  • @francescocalifano4856
    @francescocalifano4856 4 года назад +1

    I'm preparing my university exam about "Data Science and machine learning", these videos are pure gold for someone who is approaching this topics for the first time like me. Thank you so much, it was really worth the time spent to watch it.

  • @nguyenchau3800
    @nguyenchau3800 4 года назад +1

    Wow, I've been looking for this kind of explanation about LSTM in details for weeks. Thank you so much!

  • @piers9186
    @piers9186 5 лет назад +5

    Clear, unpretentious, non-shouty video. Thank you.

  • @sebastianappelt4652
    @sebastianappelt4652 7 лет назад +1

    The best explanations for CNNs and RNNs! Thank you a lot!

  • @goodmusic284
    @goodmusic284 Год назад

    The best Intro To RNNS and LSTMs I have seen!

  • @thewho2801
    @thewho2801 11 месяцев назад +1

    Thanks a lot for this straight to the point explanation. Really learnt a lot.

  • @eashansoni3761
    @eashansoni3761 6 лет назад +1

    Damn, the people who come up with these neural network architectures are brilliant.

  • @Lines-In-The-Sand1
    @Lines-In-The-Sand1 7 лет назад +3

    This is by far the best channel out there on machine learning. More please!

  • @kameziax
    @kameziax 6 лет назад +1

    Great detailed explanation! You’ve made LSTMs very easy to understand! Great Job ! Thanks a lot for your efforts!

  • @kartikpodugu
    @kartikpodugu 6 лет назад +1

    Saw many videos on explaining CNN in a simple way. This video explains RNNs and LSTMs in a simple way. Very intuitive

  • @stevecoxiscool
    @stevecoxiscool 7 лет назад +6

    Fantastic explanation. Taking the time to explain the diagram symbols really helps (me) (sigmoid/tanh/addition/multi). I also liked how the video explains that with RNN/LSTMs, you are going to need several NNs in this solution and not just one NN with lots of hidden layers (another words what DEEP really means). The other hard part for me anyways has always been data conversion, knowing that you have to obviously convert a "string name" to a numerical representation (TF/IDF) for example before you can even push the input data into a NN architecture. Thanks for your effort !!!

  • @sanjibphukan3570
    @sanjibphukan3570 4 года назад +1

    Beautifully well illustrated in simple, step by step manner for such complex concepts

  • @garrettosborne4364
    @garrettosborne4364 3 года назад +1

    Great job Brandon, simple and straightforward explanation easy to grasp concepts.

  • @AurL_69
    @AurL_69 3 месяца назад +1

    This channel is a goldmine ty

  • @piotrekgor18
    @piotrekgor18 5 лет назад +18

    after just 3 minutes i knew it is going to be a brilliant video. Thank you.

  • @carlseconds7557
    @carlseconds7557 2 года назад +1

    I don't usually place any comment like this, but this is extraordinary :) So easy to understand :) Thank you :)

  • @ardeshir1912
    @ardeshir1912 5 лет назад +1

    Great Video explaining why and how we had to modify the simple NN to achieve this. Thank you. Looking forward to more videos

  • @balmukund6181
    @balmukund6181 3 года назад +2

    Thanks so much Brandon!! I wish to learn how features are extracted from network packets. Thanks for the videos.
    Urge all to give you an upvote.😀

    • @BrandonRohrer
      @BrandonRohrer  3 года назад +1

      Thanks Balmukund! I'll keep network packets in mind as an application.

    • @balmukund6181
      @balmukund6181 3 года назад

      Thanks a lot for your reply Brandon! I am trying to use CNN algorithm for network security application for my project in my masters. Could I connect to you Sir via mail?

  • @mihkellukats4773
    @mihkellukats4773 5 лет назад

    Best graphical explanation I've seen so far. Thanks!

  • @normansabin8322
    @normansabin8322 3 года назад +2

    I love the birds chirping in the background, super calming :)

  • @gelliravikumar018
    @gelliravikumar018 5 лет назад +1

    Apreciated Brandon, Nice presentation. Crisp and precise explanation for LSTM concept.

  • @YH-fj9bs
    @YH-fj9bs 6 лет назад +6

    This video is the best one explaining the LSTM!!! Thanks you so much!!!

  • @robindong3802
    @robindong3802 5 лет назад +2

    this is first LSTM video, you gave me a confidence to go on. Thanks,

  • @vyaslkv
    @vyaslkv 5 лет назад +2

    I don't usually comment, but Mr Brandon the way you explained things really made to do this. Really superb sir _/\_

  • @khallild2288
    @khallild2288 6 лет назад +1

    I watched it 3 times and I finally get it, it's really a fantastic system. Thanks for the really good explaination

  • @ferinphilipose281
    @ferinphilipose281 6 лет назад

    Amazing explanatory video on RNN and LSTM. Thanks a ton for making it this easy to understand the LSTM concepts

  • @allisswellable
    @allisswellable 5 лет назад

    Excellent explanation of LSTM in a very simplified and realistic way... Great video!

  • @hmoazed
    @hmoazed 3 года назад +1

    Thanks for simplifying something complex so clearly that even I understood it :)

  • @BoruffAdventures
    @BoruffAdventures 6 лет назад +2

    This made LSTM clear and understandable. Also your How Deep Neural Networks Video made the abstract way a computer hones its network down a simple and clear algebra equation.

  • @frankli5075
    @frankli5075 5 лет назад +1

    Best one to explain LSTM so clearly.

  • @Vikram-wx4hg
    @Vikram-wx4hg 3 года назад

    Thanks for taking the pains to build those examples. You are explaining this wonderfully!

  • @slimyelow
    @slimyelow 2 года назад

    This is an extremely helpful and productive explanation plus creative demonstration of the RNN. Thanks so much !

  • @DanTaninecz
    @DanTaninecz 4 года назад +1

    Astonishingly great video. As an instructor, you provide a lot to emulate here.

  • @MadhurjyaBora
    @MadhurjyaBora 5 лет назад +5

    Thank you for the video. It helped me learned the concepts of RNN and LSTMs so easily

  • @japsowinkaur525
    @japsowinkaur525 2 года назад

    The best video on LSTM and RNN I've seen. Thank you so much!

  • @realcolby
    @realcolby 4 года назад +1

    Thank you so much I’ve been trying to understand LSTMs all week and this video finally did it for me

  • @MauiMana
    @MauiMana 6 лет назад +1

    Excellent walk through of fundamental LSTM concepts

  • @jaimegonzalezsuarez1566
    @jaimegonzalezsuarez1566 6 лет назад +1

    THE BEST VIDEO EXPLAINING NEURAL NETWORKS BY THE FAR you a re and amazing teacher, everything is clear you have a new fan good work

  • @easylearn9350
    @easylearn9350 5 лет назад +1

    I am beginner in DNN, I must say, I really enjoyed learning LSTM, Thanks a lot!

  • @AbhishekGupta-zx9dn
    @AbhishekGupta-zx9dn 5 лет назад +1

    By far the best explanation on this topic.

  • @NositisNation
    @NositisNation 4 года назад +1

    Just excellent. It is art to find the simple story w/n complexity. Well done sir, well done.

  • @daljeetsodhi670
    @daljeetsodhi670 6 лет назад +1

    Hi Brandon, you made my day today. Very nicely and simply explained

  • @rorycawley
    @rorycawley 6 лет назад

    The best video to learn LSTM I've seen, thanks Brandon!

  • @47292801
    @47292801 5 лет назад

    Awesome video indeed. Very abstract concepts explained in very straightforward visual figures. Really appreciate it.

  • @pallavijog912
    @pallavijog912 4 года назад +1

    This is an unbelievably amazing video that I have ever seen for RNN/LSTM.. I was looking out for exact systematic approach to explain it which is not done by anyone else.. Subscribing to your channel.. Kudos!

  • @nsaccente
    @nsaccente 5 лет назад +1

    This video was absoultely AMAZING. I've subbed and hope you keep on keeping on! Thanks so much!

  • @parvezrafi4098
    @parvezrafi4098 6 лет назад +1

    Thanks Brandon. This video provided lot of clarity in simple terms.

  • @bhesht
    @bhesht 5 лет назад +2

    What a well-organised explanation. Thank you!

  • @Apurvsankhyadhar
    @Apurvsankhyadhar 4 года назад +2

    Absolutely amazing video, especially the toy example at the end. Was struggling with Andrew's video, but combining the intuition from this video with the diagram and formulae he told, damn am I happy

  • @daulatrachmanto2353
    @daulatrachmanto2353 5 лет назад

    Tbh, this is the best video explanation about LSTM i've ever seen
    Thanks :)

  • @shridharyadav88
    @shridharyadav88 8 месяцев назад

    That was an amazing explanation. Very clear with the help of images and symbols.

  • @ajitkumar15
    @ajitkumar15 2 года назад +1

    This is really amazing video on LSTM. Pace and clarity of explanation is awsome !!! thank you Brandon

  • @parasmal2344
    @parasmal2344 5 лет назад +1

    This video clear my all doubts on LSTM , Thank you !!

  • @ocean694
    @ocean694 2 года назад

    Exceptionally good, the best I've seen in this subject.

  • @jasonhehe
    @jasonhehe 7 лет назад +1

    Amazing work. thanks Brandon, all your videos are great, to ease in this journey to learn the topic.

  • @Jabrils
    @Jabrils 6 лет назад +133

    Hey thanks for this video brandon! I learned a lot of great new LSTM knowledge. I am coming over from Luis by the way 👍

    • @NickKartha
      @NickKartha 5 лет назад

      Which Luis, Jabs?

    • @roniquinonez9715
      @roniquinonez9715 5 лет назад +4

      Luis Serrano.
      LUis Serrano's Friendly Intro to RNNs: ruclips.net/video/UNmqTiOnRfg/видео.html

    • @BrandonRohrer
      @BrandonRohrer  3 года назад +1

      Overdue on my part, but I'm so happy you found it! Thanks for the shoutout. Keep up the amazing content. You are doing great things.

    • @Leonardo-fm7fj
      @Leonardo-fm7fj 3 года назад

      @Karsyn Denver Why on earth would you like to hack your gfs instagram? What are you, a thief or something? At which country do you live in? I am sure the local police authorities would like to have a word with you or two.

  • @MarcosAG90
    @MarcosAG90 6 лет назад

    Thanks for this video!! This level of explanation is just what I needed to understand what's going on under the hood!! Thanks!

  • @georgplaz
    @georgplaz 4 года назад +1

    There are so few good videos on this topic and you nailed it. thanks!

  • @ravisawhney3111
    @ravisawhney3111 6 лет назад +1

    Great intro to RNN and LSTM for a non-developer. Will follow you.

  • @michealabaho265
    @michealabaho265 5 лет назад +1

    Awesome, Brandon. I finally get a better understanding of LSTM.

  • @ashita1130
    @ashita1130 Год назад +1

    Watching in 2x speed, even then it makes perfect sense! 🙏

  • @sridhark5819
    @sridhark5819 5 лет назад

    I will never forget LSTM , Thanks!!

  • @majeedhussain3276
    @majeedhussain3276 5 лет назад +1

    This is the best explanation on Internet

  • @mayankpj
    @mayankpj 7 лет назад +1

    very nicely put together!
    Precise and with very clear examples, couldn't be better :D ..... Thanks so much for this.

  • @mukeshonlines
    @mukeshonlines 4 года назад +1

    Very good material. Thanks for explaining in so much simple ways.

  • @robindalehayden
    @robindalehayden 6 лет назад

    Best intro to LSTM I've seen, thanks

  • @VenelinEfremov
    @VenelinEfremov 5 лет назад +1

    You are a teaching genius. Thank you.

  • @baskaisimkalmamisti
    @baskaisimkalmamisti 4 года назад +1

    I can't think any better explanation. Wonderful!