Coding A Neural Network FROM SCRATCH! (Part 2)

Поделиться
HTML-код
  • Опубликовано: 25 дек 2024

Комментарии • 52

  • @FlatterBaker
    @FlatterBaker 10 месяцев назад +7

    I smell an underrated channel.
    You are literally the savior of my science fair project, thank you so much.

  • @DarthAnimal
    @DarthAnimal 2 года назад +12

    The Brain function can be heavily simplified
    You can put the two edge cases outside of the loop, caling layers[0], and layers[layers.length-1], and having the for loop start with i=1, and run while 1 < layers.length -1

  • @willysmb-bo2vn
    @willysmb-bo2vn Год назад +16

    Hey! I'm wondering when Part 3 is coming out. Can't wait to see it!

  • @PatrykPonichtera
    @PatrykPonichtera Год назад +5

    I've seen a lot of videos about Neural Networks and yours is the one that explains it in an understandable manner (Or maybe the 10th time is the charm)
    I'm curious to see the next one

  • @voil6161
    @voil6161 2 года назад +15

    I was following along in python. Here's the code if anyone wants it. I didn't test it though because I don't really know how to use it. Tutorial was too short ):
    networkShape = [2, 4, 4, 2]
    class Layer(object):
    def __init__(self, n_inputs, n_nodes):
    self.n_nodes = n_nodes
    self.n_inputs = n_inputs
    self.weightsArray = [n_nodes, n_inputs]
    self.biasesArray = [n_nodes]
    self.nodeArray = [n_nodes]

    def forward(self, inputsArray):
    self.nodeArray = [self.n_nodes]
    for i in range(self.n_nodes):
    # Sum of the weights times inputs
    for j in range(self.n_inputs):
    self.nodeArray[i] += self.weightsArray[i, j] * inputsArray
    # Add the bias
    self.nodesArray[i] += self.biasesArray[i]

    def activation(self):
    for i in range(self.n_nodes):
    if self.nodeArray[i] < 0:
    self.nodeArray[i] = 0
    def awake():
    global layers
    # layers = Layer(len(networkShape) - 1)
    layers = []
    for i in range(len(networkShape) - 1):
    # layers[i] = Layer(networkShape[i], networkShape[i + 1])
    layers.append(Layer(networkShape[i], networkShape[i + 1]))
    def brain(inputs):
    for i in range(len(layers)):
    if i == 0:
    layers[i].forward(inputs)
    layers[i].activation()
    elif i == len(layers) - 1:
    layers[i].forward(layers[i - 1].nodeArray)
    else:
    layers[i].forward(layers[i - 1].nodeArray)
    layers[i].activation()
    return layers[-1].nodeArray

  • @drewdowsett
    @drewdowsett 2 года назад +4

    A great series. Not only for content, but well edited too. Cheers John.

  • @RealChristopherRobin
    @RealChristopherRobin 2 года назад +4

    Let's gooooo, part 3 please!

  • @mehmatrix
    @mehmatrix 2 года назад +5

    Great video. Thanks for the effort. I'm looking forward to see the part 3. Cheers,

  • @asyncmanagement
    @asyncmanagement 2 года назад +4

    we need the continuation, really

  • @slarcraft
    @slarcraft 7 месяцев назад

    Nice video! In general I'd say a neural network is still a black box even if you built it and know the values of all the nodes, weights, biases and layers.

  • @patricksturgill9441
    @patricksturgill9441 Год назад +1

    Hopefully you'll finish this eventually! I enjoyed the last two videos.

  • @bencebob8055
    @bencebob8055 Год назад

    thank you so much! this is exactly what i need for my uni project

  • @t.p.5088
    @t.p.5088 6 месяцев назад

    best video ive ever seen not gonna lie

  • @gustavosalmeron2013
    @gustavosalmeron2013 Год назад

    That was an excellent, practical video on neural networks! As someone just beginning to dig into this subject, I love it!
    Also, clean and neat code. Enjoyable to read (although I'm not a fan of nesting classes).

  • @wyrdokward2290
    @wyrdokward2290 Год назад

    Great video ! I'm really looking forward to see how the network will be trained

  • @raouftouati4711
    @raouftouati4711 2 года назад +2

    just amazing 🤩🤩

  • @DanielYong-o1k
    @DanielYong-o1k Год назад +4

    isn't the 'layer' in layer[ i ] = new Layer( networkShape[ i ], networkShape[ i + 1 ] ); supposed to be 'layers' ?

  • @Bloodbone
    @Bloodbone 2 года назад +5

    Hey! I wonder when episode 3 will come out?

    • @JohnnyCodes
      @JohnnyCodes  2 года назад +14

      Hey! I’m almost done with it, hoping to have it out in less than a week!

    • @animalracer3728
      @animalracer3728 Год назад

      @@JohnnyCodesCan’t wait for it!!!

  • @paufernandezpujol987
    @paufernandezpujol987 Год назад +3

    Hi, is part 3 coming out?

  • @gagaoqphs2052
    @gagaoqphs2052 Год назад +2

    Please Upload Part 3

  • @AlMgAgape
    @AlMgAgape Год назад +3

    part 3 how to set up in unity?

  • @danielcezario2419
    @danielcezario2419 Год назад

    amazing !!! waiting the training part

  • @TheZazatv
    @TheZazatv Год назад

    O man thank you! Such a gem content out here :) I'm a Swift Dev the code is not hard to grasp

    • @TheZazatv
      @TheZazatv Год назад

      btw is part 3 coming up or nah?

    • @JohnnyCodes
      @JohnnyCodes  Год назад +2

      @@TheZazatv Yeah been really busy with work and starting my own company (Ironically ita a video editing company). I am hoping to finish it this week but I guess that has always been the goal lol. But I am hoping this week will be the week

    • @TheZazatv
      @TheZazatv Год назад

      @@JohnnyCodes oh nice we’ll be patiently waiting. And congrats on launching ur company 🫰

    • @bigmike7112
      @bigmike7112 Год назад

      @@JohnnyCodes Still waiting :D

  • @sync_areagamer1384
    @sync_areagamer1384 2 года назад +1

    amazing

  • @morybest
    @morybest 2 года назад

    very useful John

  • @simi8220
    @simi8220 Год назад +2

    Part 3?

  • @erinleighlynch9400
    @erinleighlynch9400 Год назад +2

    :') Episode 3 where are you... this is the new Half Life 3 for me. Am I wrong in thinking the weights and biases were never given values here? should those be made in this class too?

    • @JohnnyCodes
      @JohnnyCodes  Год назад +1

      I believe you are correct the weights and biases were not given values yet, they are going to be randomly generated and then randomly modified each time the creatures reproduce. This is going to be in part 3............ someday...
      But luckily someone lifted the curse and I can now finish part 3 lmao, I responded to this amazing comment today by W_Shorts: ruclips.net/video/Ifx3kX5VQh4/видео.html&lc=UgzIeWiWP2lb2gqR8_h4AaABAg.9lUU-CvLP8G9od6BhfRwBh

  • @sonnykong1312
    @sonnykong1312 Год назад +1

    drop the training video right now!

  • @adirmugrabi
    @adirmugrabi 5 месяцев назад

    this is a much better way to do the forward pass:
    public void Forward(float[] inputsArray) {
    for (int i = 0; i < n_nodes; i++) {
    nodeArray[i] = biasesArray[i];
    for (int j = 0; j < n_inputs; j++) {
    nodeArray[i] += weightsArray[i, j] * inputsArray[j];
    }
    }
    }
    this way you don't create a new array every time.
    also the opening "{" is in the correct location.

  • @aesvarash3256
    @aesvarash3256 Год назад +2

    I wonder that the shape of network . I mean how many hidden layers and nodes should we use for each sample .
    And also wondering about third part .

  • @sync_areagamer1384
    @sync_areagamer1384 2 года назад +1

    very good :)

  • @pauldevred1393
    @pauldevred1393 Год назад

    please, do the third part

  • @adirmugrabi
    @adirmugrabi 5 месяцев назад

    if the activation function always happen right after forward. why not just combine them?

  • @thimodemoura4472
    @thimodemoura4472 Год назад +1

    i need that next video i have no idea what im doing :(
    i have this code and i think i understood how it works after starring at it for an Eternity BUT how can i make use of it now....

  • @radsy5821
    @radsy5821 Год назад

    Good tutorial, but as others have pointed out there is a compile error both in the video and the github code in Awake(). layer in the for loop should be layers. Makes me wonder if was ever tested?

    • @JohnnyCodes
      @JohnnyCodes  Год назад +2

      Yeah I am not sure how that got in there. The code definitely works because all of the clips of the training are created using this code so I must have done some refactoring to improve the names of variables for the video and had a typo. Will fix that soon

  • @TheRealTalGiladi
    @TheRealTalGiladi 8 месяцев назад

    Thank you! I would have kissed you for that great explanation!

  • @AThingProbably
    @AThingProbably Год назад +1

    what

  • @Funny9689
    @Funny9689 2 года назад

    This is useless, you literally just implemented matrix dot in C#. Most of the difficulty in making a neural network is just backprop, jfc

    • @mehmatrix
      @mehmatrix 2 года назад +20

      Clearly this is a tutorial for beginners, there is part 3 coming up and the most complicated things are built on top of simple concepts.. like matrix dot products 🤷‍♂ when you make a video that could explain backpropagation in 17 mins to beginners, please share with us. Cheers,

    • @Nabuuug
      @Nabuuug 2 года назад

      The true useless entity here is you, my dear sir.