Kaggle notebook with all the code: www.kaggle.com/wwsalmon/simpl... Blog article with more/clearer math explanation: www.samsonzhang.com/2020/11/2...
Пікірлер: 1 200
@victorafonso4534 Жыл бұрын
Making a neural network from scratch is easy, what I really want to see is how to make a neural network ON scratch.
@d3vitron779 Жыл бұрын
Make the scratch cat sentient challenge (gone wrong) (humanity destroyed)
@theRPGmaster Жыл бұрын
Just create a python interpreter in Scratch, easy
@Despatra Жыл бұрын
Ok
@v037_ Жыл бұрын
Lmao, understimated comment, but perfect one
@BurNJoE Жыл бұрын
lol
@you_just Жыл бұрын
i like how numpy has become so ingrained in python that it's basically considered vanilla python at this point
@nathanwycoff4627 Жыл бұрын
interestingly much of that functionality is built into other languages used by the ml community such as R, matlab and julia.
@mattrochford6783 Жыл бұрын
@@nathanwycoff4627 matrices and linear algebra are really useful for math and engineering less so for general programming. Different languages focusing on different usability concerns quite interesting.
@machineman8920 Жыл бұрын
@@mattrochford6783 stop coping julia is just a better language
@HilbertXVI Жыл бұрын
@@machineman8920 ???
@thebluriam Жыл бұрын
I don't like it. I wish people stopped being overly-lazy with Numpy and just wrote their own libraries so they'd understand what they are actually doing. No, scratch that, if they can't accomplish the same thing using only Assembly, they're a total noob, should put down their keyboard, and get an MBA instead...
@khoa4k2665 ай бұрын
I watched this video when I was studying in grade 11. Had no clue what he was talking about but I tried to understand as much as possible. Now I watch it again as a university student, it is so satisfying to understand everything now.
@viCuber3 ай бұрын
Hope that will happen to me to
@CR33D4043 ай бұрын
@@viCuber same LOL
@viCuber3 ай бұрын
@@CR33D404 lmao
@codevacaphe37632 ай бұрын
It happens to me several time. Sometime you just stumble on a knowledge and can't understand a single thing about it then suddenly 1 or 2 years later you completely understand it without any try.
@nachoyawnАй бұрын
same
@alperengul86543 жыл бұрын
If you make more deep learning videos with numpy and math(without any framework) just like in this video, it would be great for begginers to learn basics!!! Do you think to keep continue??
@cemsalta3 жыл бұрын
Merhaba Eren!
@kanui36183 жыл бұрын
upp!
@anishojha10203 жыл бұрын
Hey guys, a reply would be highly appreciated. I want to plot the cost vs the number of iterations but I am not able to figure which parameter to plot ? I am a beginner and I would really appreciate the help. Thank you
@KHM952 жыл бұрын
Here's a course you'll need. Face Mask Detection Using Deep Learning and Neural Networks. It's paid but it's worth it. khadymschool.thinkific.com/courses/data-science-hands-on-covid-19-face-mask-detection-cnn-open-cv
@whannabi2 жыл бұрын
@@anishojha1020 you're probably not a beginner anymore so I hope you found your answer! Unfortunately, youtube comment section isn't a forum and a lot of people disable notifications(including me) so an actual forum although people are sometimes really rude and condescending, is your best bet for future questions.
@tecknowledger3 жыл бұрын
This video is one of the best descriptions of neural networks written in only Numpy and Python I've ever seen. Thanks
@anishojha10203 жыл бұрын
Hey guys, a reply would be highly appreciated. I want to plot the cost vs the number of iterations but I am not able to figure which parameter to plot ? I am a beginner and I would really appreciate the help. Thank you
@tecknowledger3 жыл бұрын
@@anishojha1020 Hi, try posting comment again in regular comments part, so more people see it. This is only a sub-comment.
@waterspray57432 жыл бұрын
@@KHM95 Hi, are you a bot?
@KHM952 жыл бұрын
@@waterspray5743 No man, I am not.
@ME0WMERE2 жыл бұрын
I advise looking at sendex's 'Neural Network from scratch' series
@TimeRoot Жыл бұрын
00:51 Problem statement 01:18 Math explanation 11:18 Coding it up 27:43 Result's
@omgcyanide4642 Жыл бұрын
Thank you
@Zetzumarshen Жыл бұрын
Thank you
@Dejwv_ Жыл бұрын
Thank you
@Salien1999 Жыл бұрын
Thank you
@stringstudios2262 Жыл бұрын
Thank you
@jumpierwolf Жыл бұрын
Took a Machine Learning course in university and this is what we did the whole semester in Matlab. Tensorflow was introduced right at the end for the final project.
@gasun1274 Жыл бұрын
sounds amazing
@marshmellominiapple Жыл бұрын
oh hell yea matlab
@ElectrostatiCrow Жыл бұрын
@@marshmellominiapple oh he'll yeah methlab
@dumbfate9 ай бұрын
@@ElectrostatiCrow LET HIM COOK
@PluetoeInc.20 күн бұрын
@@dumbfate no you let him cook
@hcmcnae11 ай бұрын
I'm so glad you actually went in depth with the math explanation. So often people will just explain surface layer and then "alright lets jump into the code".
@MegaJesusini Жыл бұрын
My man really explained how a back propagated neural network works from scratch in 10 minutes
@LydellAaron Жыл бұрын
Just your intro alone in your motivations was so capturing. You laid out everything so clearly, including creating those row and column matrices in the early steps. Thank you.
@traviss7740 Жыл бұрын
I've never heard any of this explained before. After watching this once, I understand the mathematics behind neural networks and why the functions are used. Great job with the explanation here. Many thanks.
@Hex... Жыл бұрын
This was interesting, it certainly made neural networks far more approachable to me as someone who's never needed to/been inclined to try making one, but encounters them frequently by being involved in STEM. Your explanations coupled with my familiarity with numpy as opposed to dedicated libraries for neural networks really helped - thanks!
@Mutual_Information Жыл бұрын
Just discovered this channel. Very cool stuff. Much respect for doing something challenging like this.
@darrellrayford3817 Жыл бұрын
This was a really good video. I’ve never build a neural network but it was interesting seeing how the fundamentals add up to build something a little more complexed.
@randyscorner9434Ай бұрын
Excellent tutorial and example. Reveals the magic that most don't know about NNs and I love how you go about it.
@Bobbleheads56 Жыл бұрын
I need to come back to this after learning some more preliminaries but you are a very natural teacher and good at presenting. Keep it up 👍
@albertolemosduran5685 Жыл бұрын
Most of the videos are titled “how to create a blabla” when they’re actually teaching how to use… so I really appreciate your video! This really contributes to knowledge 🥰
@lbb2rfarangkiinok Жыл бұрын
This was really neat. The math explanation was frustrating the first time around but really made sense after working through the code. Thanks for sharing.
@mauricioledon4498 Жыл бұрын
You sir, are my hero. You are the first person to actually explain this properly to me. Thank you so much for that.
@robertknopf62073 жыл бұрын
Another thing that would be helpful for those of us that want to copy what you did and experiment with it is to have all the code together instead of separated as it is using Kaggle - this way you can put in some comments with the code explaining the different features. Again, very good video.
@KSATica Жыл бұрын
You should continue making video similar to this maybe something a training course for machine learning and reinforcement learning AI. You have a real talent for explaining it in the best way possible then from what most videos I’d watched. 👍
@omlachake25512 жыл бұрын
this type of learning is honestly the best, i implemented k means clustering by myself in c (pretty easy stuff but still) , and i can never forget it now, makes me happy that i can do stuff too
@Emily-fm7pt Жыл бұрын
When I was in high-school algebra I programmed an algebra calculator to do my homework for me, and for some reason I never actually needed it. Programming something really is a great way of learning it, even if it does take significantly longer than just some p-sets or flashcards.
@OT-tn7ci Жыл бұрын
@@Emily-fm7pt dude are you serious ??? SAME SAME lmao
@auronusben456711 ай бұрын
I remember when I tried to implement a decision tree on paper !! With a very small data dimensions (maybe 5x6 dim? Can't remember). I spent all the night doing the math but after 5-6 hours I realized I made a mistake in an iteration 😂😂 that's when I realized that we're lucky to have computers to help do it because a human mind can't build completely without doing mistakes in the process (can't stay focus for long time)... I also remember when I implemented a PCA from scratch on excel ( still have the Excel 😂)...😮
@momol.98922 күн бұрын
Just learned basics around the neural networks and saw this video. So satisfied to all the math formulas are laid out clearly in numpy and real-world coding and training neural network with back propagation. It really helps beginners like me. Thank you so much!
@jeandy4495 Жыл бұрын
Super cool! Would also recommend the series from The Coding Train about creating a neural network from scratch, going a little more into the details of math and what is a perceptron and so.
@RonClabo3 жыл бұрын
What an awesome video! Thank you for sharing this insightful walkthrough, it was really helpful in getting a better understanding of how neural nets works. Thank you!
@KHM952 жыл бұрын
Here's a course you'll need. Face Mask Detection Using Deep Learning and Neural Networks. It's paid but it's worth it. khadymschool.thinkific.com/courses/data-science-hands-on-covid-19-face-mask-detection-cnn-open-cv
@FreakyStyleytobby Жыл бұрын
Man this video is a masterpiece. I learned a lot and I love your thorough, calm style. Please keep doing similar content!! Best wishes
@minjunkevink2 жыл бұрын
Amazing. Needed to see the low end and finally found it. Thank you for the amazing video!
@anandptyagi5275 Жыл бұрын
After Andrew Ng's course, this is the first time I'm watching math functions, thanks buddy, it was a nice refresher for me.
@juliocardoza6066 Жыл бұрын
Samson, Keep doing this kind of videos please!! Very intelligent and understandable video
@luisbq80459 ай бұрын
This is pure gold, MSc in Data Science and Artificial Intelligence, no professor ever gave me the answer to "what is the code inside the libraries we use", until I found you. Thank you
@rushisy9 ай бұрын
thats sad
@stanislavlia7 ай бұрын
I don't want to sound too catchy and annoying but the NN's in Tensorflow and PyTorch are not actually implemented like this. They don't store functions to compute gradients for every single option rather they use AutoGradient which does all backpropogation job. I would highly recommend to watch Andrej Karpathy's tutorial on micrograd (mini AutoGradient which you will implement)
@michaelpieters1844Ай бұрын
I got a master in physics and statistics but I do know how to code a lot of "machine learning" techniques from scratch. Yet human resources look at my degree and think I am incapable, so they rather hire master in AI. I can also code CFD, SPH and FEA from scratch but HR say I am dumber than engineer who just uses third party software (ansys).
@suscactus42028 күн бұрын
@@michaelpieters1844 welcome to recruitment in 2024... you need to feed the recruiters what they want to hear, so that you can then get to the guy who you actually want to talk to about your stuff.
@ItsNaberius20 күн бұрын
Really excellent breakdown of a Neural Network, especially the math explanation in the beginning. I also want to say how much I appreciate you leaving in your first attempt at coding it and the mistakes you made. Coding is hard, and spending an hour debugging your code just because of one little number is so real. Great video
@joschkazimdars2 жыл бұрын
It feels like it took me months to understand programming feedforward neural networks but I finally understand it. Thanks for the video.
@faris.abuali Жыл бұрын
Thank you so much Mr. Samson!! This was so informative and enlightening
@GrahamEckel Жыл бұрын
Better lecture and example for understanding and building NN than any in my math and stats MSc
@drgatsis Жыл бұрын
Thanks for lovely video Samson. I'm a prof and love seeing this kind of content. I'll definitely share with students
@peterweicker775 ай бұрын
This is great. Built a backprop in C thirty years ago to solve the same problem. Just for a goof. It worked well before I finished debugging. These things are awesome and now I want to take another look. Thanks for posting this.
@solleo9 Жыл бұрын
What an impressive speed run! Just nitpicking: 15:45 `rand` is for a uniform dist U(0,1) and `randn` is for the standard normal distribution N(0,1), therefore unbounded, not U(-0.5, 0.5)
@chessprogramming591 Жыл бұрын
Thank you for your time and effort, Samson, this tutorial is a treasure.
@straightup7up5 ай бұрын
Samson, we need more videos like this from you. Great content, more visuals would be nice, too 🙂
@gnorts_mr_alien Жыл бұрын
This is the first ASMR NN video that I have ever seen. Well done.
@David-ip2sd Жыл бұрын
Hi! I did a recreation of your code with more hidden layers and noticed what I think is a bug in the db calculation. Changing it to db = 1 / m * np.sum(dZ, axis=1).reshape(-1, 1) was able to get me better results. I think the old db = 1 / m * np.sum(dZ) sums the entire dZ to one float. Very good video though!
@Hyngvi Жыл бұрын
noticed the same thing. The way it was implemented here returns db to a float and thus b will always be "similar" to the random initialization, only shifted up/down by a constant.
@mattlange006 ай бұрын
Hey, I know you posted this a while ago, but I noticed the same thing and saw your comment. I am still not sure how to solve this, dZ is still a 1D array (1 by 10) so in your solution, what does axis=1 do? won't .sum*() just turn the 1D array into a scalar regardless, and then you are back with the same problem of updating all your biases the same way?
@mattlange006 ай бұрын
Actually, nevermind, dZ is 10 by m so this does make sense
@gpeschke3 ай бұрын
Numpy requires some strange things when you have only 1 dimension: Verfied that without this change the final biases weights aren't being updated. With it, training works better. Didn't verify the details of David's solution, just that it was needed, and that it seemed to work. def backward_prop(Z1, A1, Z2, A2, W1, W2, X, Y): one_hot_Y = one_hot(Y) dZ2 = A2 - one_hot_Y dW2 = 1 / m * dZ2.dot(A1.T) db2 = 1 / m * np.sum(dZ2, axis=1).reshape(-1, 1) dZ1 = W2.T.dot(dZ2) * ReLU_deriv(Z1) dW1 = 1 / m * dZ1.dot(X.T) db1 = 1 / m * np.sum(dZ1, axis=1).reshape(-1, 1) return dW1, db1, dW2, db2
@jasonavina8135 Жыл бұрын
In case any beginners to ML came here wondering why they are really confused, this video isn't really for beginners and he doesn't really explain that. Its "from scratch" in the sense of not using any prebuilt models in the code. Its a good explanation for people who are already familiar with neural networks, prebuilt layers, loss functions, etc. not for people starting their understanding "from scratch."
@OT-tn7ci Жыл бұрын
actually im new to ML, (2-3 months in) and this helped me understand a lot, i am implementing it on my own now, without even using numpy so i can code out stuff like transpose on my own and learn more. Random is tricky tho lol
@edisonbekaj863 Жыл бұрын
Samson Zhang is the BEST Cinematographer, editor, musician& tech geek in the WORLD
@Crayphor Жыл бұрын
It's worth noting that softmax IS actually very similar to sigmoid. But it essentially does a sigmoid over multiple classes.
@SnackPack913 Жыл бұрын
I’m always too intimidated to try some of these things. But seeing your process makes it really seem feasible. Need to brush up on my linear algebra again tho 😆
@arksodyssey2 ай бұрын
This solved a lot of doubts and brought up mu confidence levels to deep dive into AI/ML. Thanks for the explanation.
@ricardogomes9528 Жыл бұрын
Awesome fundamental class on neural networks equations. Bravo!
@notyou4122 Жыл бұрын
Musician, filmmaker, data scientist, and etc. bro maxed out on skill trees. 😂
@AAAJ27 Жыл бұрын
Samson, this was such a great walk through. Just wanted to say that if you ever made other videos recreating machine learning models from scratch, I'd 100% watch them. In any case, hope all is good and thanks for this great content :)
@kurtameyer2 ай бұрын
Thank you. I'm doing this in class right now and your explanations were super helpful!
@llewsub7 ай бұрын
Most tutorials I watch online about ML, you can just tell that the instructor doens't know whats happening. They've just memorized libraries and tensorflow syntax, and I don't want that to be me! This is exactly what i've been looking for! THANK YOU!!!
@sharmakartikeya2 жыл бұрын
Bro, that is exactly how I study! I found out your channel and I am so glad I did. Instantly subscribed! I see you have learnt from Andrew Ng
@rishikeshkanabar46502 жыл бұрын
yeah the notations reminded me of Andrew Ng
@kumaranp87642 жыл бұрын
@@rishikeshkanabar4650 usage of the word called "intuition" reminds me of him saying ..."to get a better intuition" in his lectures
@FireNLightnin Жыл бұрын
Great video! I did the same thing in python about a year ago, but I didn’t like relying on numpy so much. Your video gave me the motivation to write both a matrix manipulator and neural network from scratch in Java
@TheJackTheLion9 ай бұрын
I did it in assembly, easy
@aureliencobb199 Жыл бұрын
Brilliant. Kind of the Hello World of neural nets. It shed a lot of light for me on how back propagation works.
@waynesletcher74704 ай бұрын
Love your sense of humor! Brought the video to life, thanks! You are appreciated!
@kiaruna Жыл бұрын
Could you please do more tutorials ? This is such a great video
@DiAMONDBACK858 ай бұрын
Hi Samson! I'm a developer and trying to learn the basics of ML. Much of the beginner stuff I see is using pre-trained models and frameworks which might be convenient to get things going. However, for me this is something completely new and I really what to understand what happens behind the scenes. Thank you for posting this! /Kevin from Sweden
@jmw15005 ай бұрын
Take the statistics course then. Don't learn from programmers. They do not know either.
@paultvshow3 ай бұрын
Exactly!
@carnap3552 ай бұрын
try jeremy howard part2 of 2022 courses
@deananderson8186 Жыл бұрын
I loved this video! Cool stuff. I implemented a tfidf clustering algorithm myself, very satisfying to see it all working
@bf300 Жыл бұрын
Really cool video Samson! Great stuff!
@mercedeszkistoth5367 Жыл бұрын
There is one thing I do not understand. Because the derivation and chain rule stuff, shouldn't the derivative of the softmax activation function also be included somewhere?
@work9466 Жыл бұрын
I actually did this exact same thing for my German a level project. Same database. :D good times
@luizarnoldchavezburgos3638 Жыл бұрын
Keep doing it man, I am from Perú and the information that your are giving is the important I have heared about
@jasonkim1642 Жыл бұрын
Great video! It's really solid in foundation! I will definitely recommend this to those just like to use framework and library without understanding
@dcrespin Жыл бұрын
An excellent nice video with abundant mathematical insight. It may be worth to note that instead of partial derivatives one can work with derivatives as the linear transformations they really are, and also looking at the networks in a more structured manner thus making clear how the basic ideas of BPP apply to much more general cases. Several steps are involved. 1.- More general processing units. Any continuously differentiable function of inputs and weights will do; these inputs and weights can belong, beyond Euclidean spaces, to any Hilbert space. Derivatives are linear transformations and the derivative of a neural processing unit is the direct sum of its partial derivatives with respect to the inputs and with respect to the weights; this is a linear transformation expressed as the sum of its restrictions to a pair of complementary subspaces. 2.- More general layers (any number of units). Single unit layers can create a bottleneck that renders the whole network useless. Putting together several units in a unique layer is equivalent to taking their product (as functions, in the sense of set theory). The layers are functions of the of inputs and of the weights of the totality of the units. The derivative of a layer is then the product of the derivatives of the units; this is a product of linear transformations. 3.- Networks with any number of layers. A network is the composition (as functions, and in the set theoretical sense) of its layers. By the chain rule the derivative of the network is the composition of the derivatives of the layers; this is a composition of linear transformations. 4.- Quadratic error of a function. ... --- Since this comment is becoming too long I will stop here. The point is that a very general viewpoint clarifies many aspects of BPP. If you are interested in the full story and have some familiarity with Hilbert spaces please google for papers dealing with backpropagation in Hilbert spaces. A related article with matrix formulas for backpropagation on semilinear networks is also available. For a glimpse into a completely new deep learning algorithm which is orders of magnitude more efficient, controllable and faster than BPP search in this platform for a video about deep learning without backpropagation; in its description there are links to a demo software. The new algorithm is based on the following very general and powerful result (google it): Polyhedrons and perceptrons are functionally equivalent. For the elementary conceptual basis of NNs see the article Neural Network Formalism. Daniel Crespin
@f.osborn1579 Жыл бұрын
Haven’t finished video yet, but this looks like the missing piece of my experience learning about neural networks at a high level…I probably lacked the linear algebra skills I have now though. Whoa! This could be incredibly exciting! I can’t wait!
@mrgenetics4063 Жыл бұрын
Nobody cares what you have to say
@DungeonMasterpiece Жыл бұрын
I've been looking for this video for 6 years.
@sanglar3623 Жыл бұрын
The yt algorithm only recommends me this now, 1 year after i've encountered a similar discontent with neural network tutorials. Still very interresting to see how someone else does it. I did give myself a bit of help by using a library called Eigen for the matrixes calculations. Very well done nice video
@themoonlight19222 жыл бұрын
Hi, i found this video very helpful for beginners. Could you please tell how you came up the equations of dz,dw and db? That would be really helpful as well
@aryamankukal1056 Жыл бұрын
watch andrew ng he copied every single equation from his course
@Nanakwaku309 Жыл бұрын
@@aryamankukal1056 I wouldn’t say he copied every equation. These equations are taught in all ML/AI courses and it is just mathematics
@aryamankukal1056 Жыл бұрын
@@Nanakwaku309 andrew's notation is a very specific and if u watch carefully he uses all of the same conventions
@tommyhuffman7499 Жыл бұрын
It's a shame it isn't taught this way in courses. Excellent video!
@dbbyres4 ай бұрын
Nicely done, Samson, thanks!
@letticonionepic9 ай бұрын
I know the Maths and Programming behind it and listening this guy doing all that on his own is pure respect from my side.
@isreallealbertsanchez11562 жыл бұрын
Timestaps if you forgot 0:51 Problem Statement 1:18 Math Explanation 11:18 Coding It up 27:43 Results
@KHM952 жыл бұрын
Here's a course you'll need. Face Mask Detection Using Deep Learning and Neural Networks. It's paid but it's worth it. khadymschool.thinkific.com/courses/data-science-hands-on-covid-19-face-mask-detection-cnn-open-cv
@Achrononmaster Жыл бұрын
@18:07 is the time stamp where the other error was made, a2 = softmax(a1) which should be a2 = softmax(z2)
@Achrononmaster Жыл бұрын
@23:30 you also see two errors, there is no axis argument for the np.sum(), the lines should be db2 = 1 / m * np.sum(dZ2) ... and ... db1 = 1 / m * np.sum(dZ1)
@Achrononmaster Жыл бұрын
And @23:00 ReLU_deriv(z) should really be return np.array(zn > 0, dtype=float) if you are aiming for good typing practice.
@elivegba8186 Жыл бұрын
I don't understand anything but wow
@ricardo58752 жыл бұрын
This is a great way to teach ANN - congrats. However, I would like to suggest you to not worry too much about the time to finish the implementation. Double-checking all steps will avoid coding errors.
@Felix14325 Жыл бұрын
Amazing video for beginners to gain an insight in how neural networks work. You just have to have programmed a simple neural net from scratch once to have a good basic understanding.
@Kaetemi6 ай бұрын
Helpful, thanks. Made my own from scratch in bare C++. From image to 32 to 16 to 10 outputs, using leaky ReLU. 96% accuracy on the test set. 🥳
@GiacomoMiola Жыл бұрын
It's a MLP, you easily computed the backpropagation step in closed form, but I wonder how those famous frameworks can compute any network's partial-derivatives tensors automatically
@elliott614 Жыл бұрын
usually the partial derivatives in backpropagation are of functions specifically chosen to be convex and have nothing to do with the problem you are working on, but are just ones that work nicely for ML algos
@jamescardenas837Ай бұрын
i have no idea what your were really saying but at the same time i do because you explained how the math is used and implemented for the code. thank you !
@nextcomputerparts10 ай бұрын
A great introduction to neural networks is Parallel Distributed Programming by Rumelhart and McLelland from about 1986. They do something similar and give a lot of additional background.
@xuxusito3 жыл бұрын
Very good video and explanation! Thanks 😊. I just would have liked it if you had explained the backprop a little more in depth. Like how the derivatives are calculated on each layer (chain rule etc.) But other than that one of the best nn videos
@KHM952 жыл бұрын
Here's a course you'll need. Face Mask Detection Using Deep Learning and Neural Networks. It's paid but it's worth it. khadymschool.thinkific.com/courses/data-science-hands-on-covid-19-face-mask-detection-cnn-open-cv
@cbeezy4733 Жыл бұрын
Perhaps I overcomplicated matters compared to your approach when I did this a couple of years ago, but like you, I wanted to program it "from scratch". My language of choice: java. I actually simulated "neurons" which were a class that stored its activation data value, and its connections to the next layer, so that it "looked" like a K_m,n graph, and the connection was an array which stored the biases along each "synapse" so to speak. Then when the hidden layers activated, I had each neuron simply sum the outputs from each synapse connecting to it from the previous layer, which was just the product of its activation value and its bias, then sigmoided this to get its own activation value. Note that while each neuron's activation was only in (-1,1), I let the biases be free parameters. When I programmed the backprop algo, I did the gradient descent the same as you, but effectively set that alpha parameter to one. It didn't occur to me to mess with that. Starting the network out with random parameters, then training it on randomly chosen sets of 10,000 images five or six times seemed to work pretty well. I saw 93% accuracy on the test data. And just for fun, I put the network on a discord bot so my friends could feed it images of the same size and see its guess. Two interesting results came out. The network fails on inverted colors: i.e., drawing white on black using MS paint or something wouldn't get reliable predictions. Secondly, using MS paint to give it new data did work, but at a much lower rate. Our best guess for why this happened was due to the sharpness of the lines between the number and backgrounds.
@youri655 Жыл бұрын
Very impressive! Great commentary/explanation as well
@hayashii5837Ай бұрын
thank you for the knowledge Mr. Samsung
@harisjaved1379 Жыл бұрын
I agree with you. I also did this by scratch. It was a lot of fun! What’s the point of masters math degree if I am not going to use it lol. Nice work!
@Pk-tw6li Жыл бұрын
bro can you help i also wanna learn can you tell us resources which you use to learn this neural network
@juliopaniagua8723 Жыл бұрын
@@Pk-tw6li study some basic linear algebra, just with that you'll understand at least 85% of whats going on with the algorithm
@Ari-Matti.Rintala Жыл бұрын
Amazing stuff! Just wondering what value does the coding timer add to the video? I mean instead of correcting your mistakes with overlapping text you could have taken a little bit of time to review your code instead of rushing it through. But again, amazing content!
@ignaciomaureirajofre435311 ай бұрын
Great explanation Sam!
@williamzhang6955 Жыл бұрын
That is very neat and captures the fundamental ideas of neural nets! great job
@danielniels223 жыл бұрын
Hello, it's such a great tutorial. thank you very much. I think people who are over exited because of this AI-hyped should learn this basic, and see whether those people really fit in to this field 🤣🤣
@ashtonoates4798 Жыл бұрын
Hey, the video was very informative for a beginner to machine learning. I did have a question about the code, I noticed that when I implemented the code as you did in the video I was getting an error: RuntimeWarning: invalid value encountered in true_divide in the softmax function. I looked at your kaggle notebook, and I see that in the notebook you do x_train = x_train / 255 and when I did this it fixed the error. I'm not sure what's going on here, does anyone know why this is happening and why dividing by 255 fixed the issue?
@gillesvanlommel5932 Жыл бұрын
Images consist of pixels, each pixel is a value between 0 and 255. Here 0 is dark and 255 is white. To make it easy, models train more easily on normalised data/ there are function that expect your data to be between 0 and 1 hence dividing every pixel value by 255. When you write it yourself, you can choose ofcorse if u want 0,255 or 0,1 but normally is its 0,1 since then if you're using it on another project with idk different pixel value it will still work. To put it simply it generalises things. Hope it helps =D!
@chriswysocki8816 Жыл бұрын
Hey, I also found this needed correction (/255) when I was coding along. But despite that I cannot get the code to work. I get an error in the "clever" function one_hot(Y). Python is telling me: "ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()" Any ideas? I'll be looking for the cause myself on the meantime
@kadenmoss8904 Жыл бұрын
@@chriswysocki8816 I was having a very similar issue. In the end, I looked at the notebook he posted to kaggle and found a couple slight differences, notably in the backward_prop function and its implementation. I don't know exactly what did it, but copying the notebook rather than the video got mine to work
@chriswysocki8816 Жыл бұрын
@@kadenmoss8904 I forgot to post, but I did find the problems and got it to work. Only then I compared it with kaggle, which would have saved me time, but less satisfaction. Anyway, still a great tutorial as now I can create these simple neural networks. I even expanded this one to 3 levels of "weights" and it worked great as it gave me a better asymptotic recognition rate (i.e. when cranking up the number of learning iterations)
@Zeoytaccount Жыл бұрын
This thread was a lifesaver lol. Does anyone understand what the line _,m_train = X_train.shape (under X_train = X_train / 255.) does? Not familiar with the API yet
@katarzynaludwikakowalczyk-8232Ай бұрын
Samson, thank you for this video, it is very helpful! Just like you, I also benefit much more from detailed, equation-based explanations than from the high level, big picture overviews.
@Theeoldmann Жыл бұрын
Really appreciate the example & tutorial, thank you. Can you make another video? Perhaps on adding more hidden layers?
@quanduong89173 жыл бұрын
You can actually use momentum for gradient descent. The result is slightly better (I tried on your nn and it gets 91% accuracy) // I'm a beginner at ML so your video taught me a lot. Keep up your great work you're doing man. It's really cool.
@akainu36683 жыл бұрын
can you please send link of your code
@123arskas Жыл бұрын
Just 1 minute in the video and I can easily tell that you're gonna own a multi-billion company within a few years. You've got the IQ, the voice, the clarity, the confidence, and the right personality. Best of luck Mr. Zhang
@iggzistentialism845811 ай бұрын
This was really useful to me, and incredibly well explained. Thank you.
@iwasdeleted7088 ай бұрын
the fact he actually shows the first overconfident of its memory programer stage is actually so real.
@Milorae Жыл бұрын
Everyone praises this video for being so helpful and I'm just sitting here understanding NOTHING. :D I feel so dumb! Maybe I should've stared with something even more basic having learned in a nutshell only print("hello world") so far. I will definitely go back and watch it all again in the future after I learn more. Thank you for the video, Samson. Cheers!
@xianzai_ad1928 Жыл бұрын
defintely pick up a book on algorithims and data structures first!
@nitinrohit16692 жыл бұрын
Hey, I found a flaw in your code and would be great if you answer it......The updation that you are doing for the bias' is not all needed as per your code because all the bias are changed by same factor hence it's still random( you have used a scalar to update the bias instead of a column vector)......I found the correct solution to it but getting an error. you should add the axis=1 in the sum function.
@lucasphillips2177 Жыл бұрын
ya I encountered that, too and fixed it like you said.
@carloscortes23914 ай бұрын
I am going to do the same over the next two weeks , at the end I'm coming back to see any differences between our code, thanks for sharing :)
@my1408194727 күн бұрын
I heard your name as Samsung- got instantly hooked.
@ReBufff Жыл бұрын
Now build one IN Scratch
@be7256 Жыл бұрын
been done actually
@fengzhang90523 жыл бұрын
Thank you for sharing . You did a awesome explanation! A quick question, I got brunch of NaN in A2 after Softmax. Besides, can you please re-share the code link? The current link connects to 404 page 😂
@bagavanmarakathalingasivam71173 жыл бұрын
The Description link wasn't working for me either, but I found the actual link: www.kaggle.com/wwsalmon/simple-mnist-nn-from-scratch-numpy-no-tf-keras?scriptVersionId=47652503
@nq2c3 жыл бұрын
U need to normalise ur values because they overflow since exponential makes numbers big try using logsumexp or something that lowers ur values
@SamsonZhangTheSalmon3 жыл бұрын
Thanks for the catch! I've updated the link
@KHM952 жыл бұрын
Here's a course you'll need. Face Mask Detection Using Deep Learning and Neural Networks. It's paid but it's worth it. khadymschool.thinkific.com/courses/data-science-hands-on-covid-19-face-mask-detection-cnn-open-cv
@jonisamuels2 жыл бұрын
I’m having the same problem, getting NaNs in a2 after using softmax(). How did you solve this? It means I can’t get actual answers out.