Building a neural network FROM SCRATCH (no Tensorflow/Pytorch, just numpy & math)

Kaggle notebook with all the code: www.kaggle.com/wwsalmon/simpl...
Blog article with more/clearer math explanation: www.samsonzhang.com/2020/11/2...

[@victorafonso4534]

Making a neural network from scratch is easy, what I really want to see is how to make a neural network ON scratch.

[@d3vitron779]

Make the scratch cat sentient challenge (gone wrong) (humanity destroyed)

[@theRPGmaster]

Just create a python interpreter in Scratch, easy

[@Despatra]

Ok

[@v037_]

Lmao, understimated comment, but perfect one

[@BurNJoE]

lol

[@you_just]

i like how numpy has become so ingrained in python that it's basically considered vanilla python at this point

[@nathanwycoff4627]

interestingly much of that functionality is built into other languages used by the ml community such as R, matlab and julia.

[@mattrochford6783]

@@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]

@@mattrochford6783 stop coping julia is just a better language

[@HilbertXVI]

@@machineman8920 ???

[@thebluriam]

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...

[@khoa4k266]

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.

[@viCuber]

Hope that will happen to me to

[@CR33D404]

@@viCuber same LOL

[@viCuber]

@@CR33D404 lmao

[@codevacaphe3763]

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.

[@nachoyawn]

same

[@alperengul8654]

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??

[@cemsalta]

Merhaba Eren!

[@kanui3618]

upp!

[@anishojha1020]

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

[@KHM95]

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

[@whannabi]

@@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.

[@tecknowledger]

This video is one of the best descriptions of neural networks written in only Numpy and Python I've ever seen. Thanks

[@anishojha1020]

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

[@tecknowledger]

@@anishojha1020 Hi, try posting comment again in regular comments part, so more people see it. This is only a sub-comment.

[@waterspray5743]

@@KHM95 Hi, are you a bot?

[@KHM95]

@@waterspray5743 No man, I am not.

[@ME0WMERE]

I advise looking at sendex's 'Neural Network from scratch' series

[@TimeRoot]

00:51 Problem statement 01:18 Math explanation 11:18 Coding it up 27:43 Result's

[@omgcyanide4642]

Thank you

[@Zetzumarshen]

Thank you

[@Dejwv_]

Thank you

[@Salien1999]

Thank you

[@stringstudios2262]

Thank you

[@jumpierwolf]

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]

sounds amazing

[@marshmellominiapple]

oh hell yea matlab

[@ElectrostatiCrow]

​@@marshmellominiapple oh he'll yeah methlab

[@dumbfate]

@@ElectrostatiCrow LET HIM COOK

[@PluetoeInc.]

@@dumbfate no you let him cook

[@hcmcnae]

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]

My man really explained how a back propagated neural network works from scratch in 10 minutes

[@LydellAaron]

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]

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...]

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]

Just discovered this channel. Very cool stuff. Much respect for doing something challenging like this.

[@darrellrayford3817]

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.

[@randyscorner9434]

Excellent tutorial and example. Reveals the magic that most don't know about NNs and I love how you go about it.

[@Bobbleheads56]

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]

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]

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]

You sir, are my hero. You are the first person to actually explain this properly to me. Thank you so much for that.

[@robertknopf6207]

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]

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. 👍

[@omlachake2551]

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]

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]

@@Emily-fm7pt dude are you serious ??? SAME SAME lmao

[@auronusben4567]

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.9892]

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]

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.

[@RonClabo]

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!

[@KHM95]

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]

Man this video is a masterpiece. I learned a lot and I love your thorough, calm style. Please keep doing similar content!! Best wishes

[@minjunkevink]

Amazing. Needed to see the low end and finally found it. Thank you for the amazing video!

[@anandptyagi5275]

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]

Samson, Keep doing this kind of videos please!! Very intelligent and understandable video

[@luisbq8045]

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

[@rushisy]

thats sad

[@stanislavlia]

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)

[@michaelpieters1844]

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).

[@suscactus420]

@@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.

[@ItsNaberius]

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

[@joschkazimdars]

It feels like it took me months to understand programming feedforward neural networks but I finally understand it. Thanks for the video.

[@faris.abuali]

Thank you so much Mr. Samson!! This was so informative and enlightening

[@GrahamEckel]

Better lecture and example for understanding and building NN than any in my math and stats MSc

[@drgatsis]

Thanks for lovely video Samson. I'm a prof and love seeing this kind of content. I'll definitely share with students

[@peterweicker77]

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]

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]

Thank you for your time and effort, Samson, this tutorial is a treasure.

[@straightup7up]

Samson, we need more videos like this from you. Great content, more visuals would be nice, too 🙂

[@gnorts_mr_alien]

This is the first ASMR NN video that I have ever seen. Well done.

[@David-ip2sd]

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]

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.

[@mattlange00]

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?

[@mattlange00]

Actually, nevermind, dZ is 10 by m so this does make sense

[@gpeschke]

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]

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]

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]

Samson Zhang is the BEST Cinematographer, editor, musician& tech geek in the WORLD

[@Crayphor]

It's worth noting that softmax IS actually very similar to sigmoid. But it essentially does a sigmoid over multiple classes.

[@SnackPack913]

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 😆

[@arksodyssey]

This solved a lot of doubts and brought up mu confidence levels to deep dive into AI/ML. Thanks for the explanation.

[@ricardogomes9528]

Awesome fundamental class on neural networks equations. Bravo!

[@notyou4122]

Musician, filmmaker, data scientist, and etc. bro maxed out on skill trees. 😂

[@AAAJ27]

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 :)

[@kurtameyer]

Thank you. I'm doing this in class right now and your explanations were super helpful!

[@llewsub]

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!!!

[@sharmakartikeya]

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

[@rishikeshkanabar4650]

yeah the notations reminded me of Andrew Ng

[@kumaranp8764]

@@rishikeshkanabar4650 usage of the word called "intuition" reminds me of him saying ..."to get a better intuition" in his lectures

[@FireNLightnin]

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

[@TheJackTheLion]

I did it in assembly, easy

[@aureliencobb199]

Brilliant. Kind of the Hello World of neural nets. It shed a lot of light for me on how back propagation works.

[@waynesletcher7470]

Love your sense of humor! Brought the video to life, thanks! You are appreciated!

[@kiaruna]

Could you please do more tutorials ? This is such a great video

[@DiAMONDBACK85]

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

[@jmw1500]

Take the statistics course then. Don't learn from programmers. They do not know either.

[@paultvshow]

⁠Exactly!

[@carnap355]

try jeremy howard part2 of 2022 courses

[@deananderson8186]

I loved this video! Cool stuff. I implemented a tfidf clustering algorithm myself, very satisfying to see it all working

[@bf300]

Really cool video Samson! Great stuff!

[@mercedeszkistoth5367]

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]

I actually did this exact same thing for my German a level project. Same database. :D good times

[@luizarnoldchavezburgos3638]

Keep doing it man, I am from Perú and the information that your are giving is the important I have heared about

[@jasonkim1642]

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]

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]

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]

Nobody cares what you have to say

[@DungeonMasterpiece]

I've been looking for this video for 6 years.

[@sanglar3623]

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

[@themoonlight1922]

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]

watch andrew ng he copied every single equation from his course

[@Nanakwaku309]

@@aryamankukal1056 I wouldn’t say he copied every equation. These equations are taught in all ML/AI courses and it is just mathematics

[@aryamankukal1056]

@@Nanakwaku309 andrew's notation is a very specific and if u watch carefully he uses all of the same conventions

[@tommyhuffman7499]

It's a shame it isn't taught this way in courses. Excellent video!

[@dbbyres]

Nicely done, Samson, thanks!

[@letticonionepic]

I know the Maths and Programming behind it and listening this guy doing all that on his own is pure respect from my side.

[@isreallealbertsanchez1156]

Timestaps if you forgot 0:51 Problem Statement 1:18 Math Explanation 11:18 Coding It up 27:43 Results

[@KHM95]

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]

@18:07 is the time stamp where the other error was made, a2 = softmax(a1) which should be a2 = softmax(z2)

[@Achrononmaster]

@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]

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]

I don't understand anything but wow

[@ricardo5875]

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]

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.

[@Kaetemi]

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]

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]

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

[@jamescardenas837]

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 !

[@nextcomputerparts]

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.

[@xuxusito]

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

[@KHM95]

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]

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]

Very impressive! Great commentary/explanation as well

[@hayashii5837]

thank you for the knowledge Mr. Samsung

[@harisjaved1379]

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]

bro can you help i also wanna learn can you tell us resources which you use to learn this neural network

[@juliopaniagua8723]

@@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]

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!

[@ignaciomaureirajofre4353]

Great explanation Sam!

[@williamzhang6955]

That is very neat and captures the fundamental ideas of neural nets! great job

[@danielniels22]

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]

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]

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]

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]

@@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]

@@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]

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-8232]

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]

Really appreciate the example & tutorial, thank you. Can you make another video? Perhaps on adding more hidden layers?

[@quanduong8917]

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.

[@akainu3668]

can you please send link of your code

[@123arskas]

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

[@iggzistentialism8458]

This was really useful to me, and incredibly well explained. Thank you.

[@iwasdeleted708]

the fact he actually shows the first overconfident of its memory programer stage is actually so real.

[@Milorae]

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]

defintely pick up a book on algorithims and data structures first!

[@nitinrohit1669]

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]

ya I encountered that, too and fixed it like you said.

[@carloscortes2391]

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 :)

[@my14081947]

I heard your name as Samsung- got instantly hooked.

[@ReBufff]

Now build one IN Scratch

[@be7256]

been done actually

[@fengzhang9052]

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 😂

[@bagavanmarakathalingasivam7117]

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

[@nq2c]

U need to normalise ur values because they overflow since exponential makes numbers big try using logsumexp or something that lowers ur values

[@SamsonZhangTheSalmon]

Thanks for the catch! I've updated the link

[@KHM95]

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

[@jonisamuels]

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.