Simple Deep Neural Networks for Text Classification

แชร์
ฝัง
  • เผยแพร่เมื่อ 25 พ.ย. 2024

ความคิดเห็น • 80

  • @Posejdonkon
    @Posejdonkon ปีที่แล้ว

    Hey there! I normally don’t leave comments, or likes but I had to stop here!
    You’ve explained a convoluted topic in a clear, digestible and concise way. Thank you!

  • @maxlegnar7639
    @maxlegnar7639 3 ปีที่แล้ว +8

    Thank you for the good explanation!
    You forgot to link the paper you mentioned (at 12:43). For all who are interested: I think it was about this paper:
    "Convolutional Neural Networks for Sentence Classification" by Yoon Kim

  • @louisd695
    @louisd695 2 ปีที่แล้ว

    this is the best explanation i've seen on CNN applied on text input

  • @danm2092
    @danm2092 5 ปีที่แล้ว +1

    This is the most comprehensive video I've ever seen on neural networks! Thank you so much! I study and develop AI, but was using something more like the bag of words representation. The other thing, aside from accuracy that I noticed to be an issue with the bag of words representation, was actually the amount of resources it required from the machine it was operating on. To give some insight into just how bad it was, while the machine I was using wasn't exactly top of the line, the machine I'm using now is pretty high performance (i5-8400, 16gb RAM, 1TB Samsung Evo 860 SSD) and yet, the facial recognition usually dropped down the camera feed to about 3-5fps when it would detect a face. Even generating a response (using Speech-to-Text, then a custom-tailored version of the Levenshtein Distance algorithm to correct any misinterpretation of speech) was using at least 7GB of RAM even with a relatively small data set in the vicinity of maybe 50GB, and using 40-60% of my CPU power. Anyhow, my intent with watching this video was to learn about better algorithms, with the intent of actually implementing a neural network on an FPGA (Field-Programmable-Gate-Array). Now I feel well-equipped with enough information to conquer that finally, as I feel I finally understand CNNs well enough. Thanks so much!

    • @MachineLearningTV
      @MachineLearningTV  5 ปีที่แล้ว

      Thanks for your feedback

    • @Mark-wl2gn
      @Mark-wl2gn 4 ปีที่แล้ว

      How would you go about getting started if you have a decent grasp of python and are trying to get into the space?

    • @xl000
      @xl000 3 ปีที่แล้ว

      This is not a pretty high performance setup. This is an average PC
      I bought a PC for 3d rendering and it's a 32 cores CPU E5-2670 0 @ 2.60GHz, 128GB of RAM and storage is a some kind of SSD on PCI-E. Pretty good setup

    • @GameChanger77
      @GameChanger77 2 ปีที่แล้ว

      i5-8400 is horrible lol, definitely not high performance.

    • @danm2092
      @danm2092 2 ปีที่แล้ว

      @@GameChanger77 Dude this post was from 3 years ago. Also, thank you for wasting both of our time by commenting this! Have a great day

  • @manjuappu89
    @manjuappu89 6 ปีที่แล้ว +16

    One of best lecture i have heard ever. Seriously i was totally in to your video for 15mins, which i forgot external world. Awaiting for next set of topics.

    • @MachineLearningTV
      @MachineLearningTV  6 ปีที่แล้ว +1

      Soon we will upload the next video of this series! If you liked the video, please press the like button so that other people can find this video!
      Regards

    • @manjuappu89
      @manjuappu89 6 ปีที่แล้ว +1

      I have subscribed, added push notification, liked videos.

    • @hellochii1675
      @hellochii1675 5 ปีที่แล้ว

      @@MachineLearningTV at 11:19 I am confused about why each gram we learn 100 filters? What is the filter in this case? I thought by applying the 3-gram kernel using the same padding, we will get (1,n) vector, where n: number of words in this case n=5. Then we have 3,4,5 gram, shouldn't we just have 3 (1,n) vectors? If we get max value for each gram, shouldn't we just have 3 outputs, where each output from each x-gram vector (size =(1,n))? Can you explain why you said 300 outputs? Thanks,

  • @boooo6789
    @boooo6789 4 ปีที่แล้ว +9

    2:05 freudian slip? made me crack up haha
    Excellent video, thanks for sharing!

  • @NandishA
    @NandishA 5 ปีที่แล้ว

    One of the best videos to understand string inputs for Neural Nets.

  • @sylvainbzh7171
    @sylvainbzh7171 5 ปีที่แล้ว +13

    Really nice explanations even if the convolution network internals are not enough explained.

  • @because2022
    @because2022 ปีที่แล้ว

    Great content.

  • @felipela2227
    @felipela2227 ปีที่แล้ว

    Your explanation was great, thx

  • @levelup862
    @levelup862 3 ปีที่แล้ว +1

    Wonderful explanation.

  • @tantzer6113
    @tantzer6113 2 ปีที่แล้ว

    How does this compare with the attention mechanism in transformers?

  • @barax9462
    @barax9462 3 ปีที่แล้ว

    at 1:54 what are the inputs are they [very, good, movie] or are they the [x1, x2, x3].

  • @hellochii1675
    @hellochii1675 5 ปีที่แล้ว

    at 11:19 I am confused about why each gram we learn 100 filters? What is the filter in this case? I thought by applying the 3-gram kernel using the same padding, we will get (1,n) vector, where n: number of words in this case n=5. Then we have 3,4,5 gram, shouldn't we just have 3 (1,n) vectors? If we get max value for each gram, shouldn't we just have 3 outputs, where each output from each x-gram vector (size =(1,n))? Can you explain why you said 300 outputs? Thanks,

  • @argentineinformationservic2917
    @argentineinformationservic2917 3 ปีที่แล้ว

    Please, explain the meaning of the final vector obtained after the 1d convolution and i guess, trained in some way.

  • @kushshri05
    @kushshri05 5 ปีที่แล้ว

    IT is the best explanation of word embeddings ever seen

  • @johntsirigotis8161
    @johntsirigotis8161 3 ปีที่แล้ว

    Where did the 0.9 and 0.84 come from? Sorry, I'm new to this...

  • @GamerBat3112
    @GamerBat3112 4 ปีที่แล้ว +1

    how to find values for convolution filter?

  • @ijeffking
    @ijeffking 5 ปีที่แล้ว +4

    Fantastic! You have explained it very very well. Please upload more videos on related and Machine Learning topics. Thank you so much.

  • @arnetmitarnetmit9456
    @arnetmitarnetmit9456 3 ปีที่แล้ว

    at 4:25, the result of convolution is not 0.9, it is 0.88. How CNN create these filters? For instance we defined 16 filters to apply. How CNN library determine the content of filters ( numbers) ?

    • @MachineLearningTV
      @MachineLearningTV  3 ปีที่แล้ว

      Good question! These filters are learned through back-propagation!

  • @rialtosan
    @rialtosan 2 ปีที่แล้ว

    excuse my stupidity, on 4:19 how do you get 0.9 from word embeddings and convolutional filter, is it a dot product? or some thing else?

  • @bismeetsingh352
    @bismeetsingh352 4 ปีที่แล้ว

    What about the context of the text. Why would you use this rather than use something like a GRU or LSTM

  • @luislptigres
    @luislptigres 5 ปีที่แล้ว +2

    Excellent video. This video made me watch the whole playlist

  • @DanielWeikert
    @DanielWeikert 6 ปีที่แล้ว +2

    Great work thanks. Can't wait for the next. Very well explained

    • @mikkaruru
      @mikkaruru 6 ปีที่แล้ว

      Try original course: www.coursera.org/learn/language-processing

  • @akashkewar
    @akashkewar 4 ปีที่แล้ว +1

    This is just brilliant!

  • @arsalaanshaikh3079
    @arsalaanshaikh3079 4 ปีที่แล้ว

    Need your advice for my ML project. Please help

  • @sonar_kella
    @sonar_kella 5 ปีที่แล้ว

    Thank you so much. Got clear idea.

  • @bizzatulhasan4629
    @bizzatulhasan4629 4 ปีที่แล้ว

    Brilliant! Please share link to the next lecture.

    • @MachineLearningTV
      @MachineLearningTV  4 ปีที่แล้ว

      Dear, in the description of the video you can find the link of the course.

    • @shubhammittal7832
      @shubhammittal7832 4 ปีที่แล้ว

      @@MachineLearningTV I dint find any links in the description. Please provide the link

  • @HeduAI
    @HeduAI 5 ปีที่แล้ว

    Amazing explanation! Thank you!

  • @epictrollmemeface3946
    @epictrollmemeface3946 3 ปีที่แล้ว

    1:20 "good movie very" ?

  • @jonathancardozo
    @jonathancardozo 3 ปีที่แล้ว

    Excelente

  • @redyandrimof7565
    @redyandrimof7565 5 ปีที่แล้ว

    Thanks man. May God guide you.

  • @singhRajshree
    @singhRajshree 5 ปีที่แล้ว

    do we always need a vector representation before neural network??

    • @ruslanmurtazin7918
      @ruslanmurtazin7918 5 ปีที่แล้ว

      Yup

    • @singhRajshree
      @singhRajshree 5 ปีที่แล้ว

      @@ruslanmurtazin7918 but that may be in case for feature eng in unsupervised learning. What about supervised learning algo..do we still need i this case?

  • @rogerfroud300
    @rogerfroud300 4 ปีที่แล้ว

    This seems to use lots of terms that are undefined here. Is this part of a larger presentation? If so, numbering the parts would be useful.
    If not, then this really expect you to know a lot about the terminology before watching. Frankly, I find this completely confusing.

  • @TheMightyWolfie
    @TheMightyWolfie 5 ปีที่แล้ว

    Can you please tell me the precision and recall of this network?

  • @mawadaabdallah5363
    @mawadaabdallah5363 4 ปีที่แล้ว +1

    great efforts!!

  • @ijash-yt
    @ijash-yt 5 ปีที่แล้ว

    what do i need to learn before can follow this video? i can't follow the explanation after hearing "bags of words" and the "neural network"

    • @Ragnarok540
      @Ragnarok540 3 ปีที่แล้ว

      Linear algebra would be a start.

    • @ijash-yt
      @ijash-yt 3 ปีที่แล้ว

      @@Ragnarok540 thanks man

  • @sachadu779
    @sachadu779 5 ปีที่แล้ว +1

    top vidéo thanks !!!

  • @sangitasable6919
    @sangitasable6919 4 ปีที่แล้ว

    thx sir its very nice lecture, i wanted to text processing on web page content can you take lecture on this

  • @Manu-lc4ob
    @Manu-lc4ob 4 ปีที่แล้ว

    How does one learn these filters?

    • @MachineLearningTV
      @MachineLearningTV  4 ปีที่แล้ว +1

      These filters are learned by the Deep Learning algorithm. As a matter of fact, these filters are the weights that Neural Networks try to learn.

  • @kuchkrgujrnahai2214
    @kuchkrgujrnahai2214 4 ปีที่แล้ว

    Sir mujhe bhi sikhna hai please🙏

  • @pedroherreroherrero1360
    @pedroherreroherrero1360 4 ปีที่แล้ว

    Sorry, but I do not understand why you do not use 2-grams windows. Without them the 2-grams are not taken into account.

  • @barkatullah7366
    @barkatullah7366 4 ปีที่แล้ว

    Please send me the paper link

  • @bhahubaliashish9853
    @bhahubaliashish9853 ปีที่แล้ว

    It’s elon musk from 2019

  • @ruslanmurtazin7918
    @ruslanmurtazin7918 5 ปีที่แล้ว

    TFW you google in english but end up watching a russian video.

  • @allahbismillahturks
    @allahbismillahturks 5 ปีที่แล้ว

    Link to the paper please?

  • @phdbakalemmahdia8446
    @phdbakalemmahdia8446 5 ปีที่แล้ว

    Very interesting video .... I need your Email...

  • @phdbakalemmahdia8446
    @phdbakalemmahdia8446 5 ปีที่แล้ว

    I need code source please

  • @Talk2Asap
    @Talk2Asap 4 ปีที่แล้ว

    a kala