Loading video...

Video Failed to Load

Go Home

A 2-layer neural network goes from total chaos to perfectly separating left vs right classes in real time. Watch the decision boundary form live as gradient descent works its magic! Pure maths beauty in motion..

mathemetica's profile picture

Mathematica

52,905 subscribers

145,102 views • 4 months ago •via X (Twitter)

EducationScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Trained a single layer neural network in C to predict AND GATE from scratch using gradient descent and Batch training of dataset in almost 300K epochs
0:22

Trained a single layer neural network in C to predict AND GATE from scratch using gradient descent and Batch training of dataset in almost 300K epochs

AADITYANSHA

81,238 views • 4 months ago

I used Claude Fable 5 to turn network traffic into an ant colony. Packets are ants. When the network gets congested, ants pile up in the tunnels. When packet loss hits, a spider shows up and eats them. There's a live dashboard tracking everything in real time. You can watch the whole network go from healthy to total chaos in 30 seconds.
0:27

I used Claude Fable 5 to turn network traffic into an ant colony. Packets are ants. When the network gets congested, ants pile up in the tunnels. When packet loss hits, a spider shows up and eats them. There's a live dashboard tracking everything in real time. You can watch the whole network go from healthy to total chaos in 30 seconds.

Alex Prompter

13,076 views • 1 month ago

a playlist of 30 youtube videos to learn machine learning fundamentals from scratch if you're struggling on where to start learning ML, this list goes this "Machine Learning: Teach by Doing" is a solid choice to learn both theory and code. (1) Introduction to Machine Learning Teach by Doing: (2) What is Machine Learning? History of Machine Learning: (3) Types of ML Models: (4) 6 steps of any ML project: (5) Install Python and VSCode and run your first code: (6) Linear Classifiers Part 1: (7) Linear Classifiers Part 2: (8) Jupyter Notebook, Numpy and Scikit-Learn: (9) Running the Random Linear Classifier Algorithm in Python: (10) The oldest ML model - Perceptron: (11) Coding the Perceptron: (12) Perceptron Convergence Theorem: (13) Magic of features in Machine Learning: (14) One hot encoding: (15) Logistic Regression Part 1: (16) Cross Entropy Loss: (17) How gradient descent works: (18) Logistic Regression from scratch in Python: (19) Introduction to Regularization: (20) Implementing Regularization in Python: (21) Linear Regression Introduction: (22) Ordinary Least Squares step by step implementation: (23) Ridge regression fundamentals and intuition: (24) Regression recap for interviews: (25) Neural network architecture in 30 minutes: (26) Backpropagation intuition: (27) Neural network activation functions: (28) Momentum in gradient descent: (29) Hands on neural network training in Python: (30) Introduction to Convolutional Neural Networks (CNNs):
0:52

a playlist of 30 youtube videos to learn machine learning fundamentals from scratch if you're struggling on where to start learning ML, this list goes this "Machine Learning: Teach by Doing" is a solid choice to learn both theory and code. (1) Introduction to Machine Learning Teach by Doing: (2) What is Machine Learning? History of Machine Learning: (3) Types of ML Models: (4) 6 steps of any ML project: (5) Install Python and VSCode and run your first code: (6) Linear Classifiers Part 1: (7) Linear Classifiers Part 2: (8) Jupyter Notebook, Numpy and Scikit-Learn: (9) Running the Random Linear Classifier Algorithm in Python: (10) The oldest ML model - Perceptron: (11) Coding the Perceptron: (12) Perceptron Convergence Theorem: (13) Magic of features in Machine Learning: (14) One hot encoding: (15) Logistic Regression Part 1: (16) Cross Entropy Loss: (17) How gradient descent works: (18) Logistic Regression from scratch in Python: (19) Introduction to Regularization: (20) Implementing Regularization in Python: (21) Linear Regression Introduction: (22) Ordinary Least Squares step by step implementation: (23) Ridge regression fundamentals and intuition: (24) Regression recap for interviews: (25) Neural network architecture in 30 minutes: (26) Backpropagation intuition: (27) Neural network activation functions: (28) Momentum in gradient descent: (29) Hands on neural network training in Python: (30) Introduction to Convolutional Neural Networks (CNNs):

ℏεsam

117,570 views • 1 year ago

💫 Welcome back to the Star Garden Showcase! The Turn Star is a Lumi vehicle evolution that builds speed while turning. Take wide corners or snake by weaving left and right to stay fast. This form rewards control and staying in motion. Watch as chaomix explains how it works!
1:39

💫 Welcome back to the Star Garden Showcase! The Turn Star is a Lumi vehicle evolution that builds speed while turning. Take wide corners or snake by weaving left and right to stay fast. This form rewards control and staying in motion. Watch as chaomix explains how it works!

Game Garage ⚙️

12,831 views • 1 year ago

if you're struggling on where to start learning ML, here’s a playlist of 30 youtube videos to learn machine learning fundamentals from scratch "Machine Learning: Teach by Doing" is a solid choice to learn both theory and code. (1) Introduction to Machine Learning Teach by Doing: (2) What is Machine Learning? History of Machine Learning: (3) Types of ML Models: (4) 6 steps of any ML project: (5) Install Python and VSCode and run your first code: (6) Linear Classifiers Part 1: (7) Linear Classifiers Part 2: (8) Jupyter Notebook, Numpy and Scikit-Learn: (9) Running the Random Linear Classifier Algorithm in Python: (10) The oldest ML model - Perceptron: (11) Coding the Perceptron: (12) Perceptron Convergence Theorem: (13) Magic of features in Machine Learning: (14) One hot encoding: (15) Logistic Regression Part 1: (16) Cross Entropy Loss: (17) How gradient descent works: (18) Logistic Regression from scratch in Python: (19) Introduction to Regularization: (20) Implementing Regularization in Python: (21) Linear Regression Introduction: (22) Ordinary Least Squares step by step implementation: (23) Ridge regression fundamentals and intuition: (24) Regression recap for interviews: (25) Neural network architecture in 30 minutes: (26) Backpropagation intuition: (27) Neural network activation functions: (28) Momentum in gradient descent: (29) Hands on neural network training in Python: (30) Introduction to Convolutional Neural Networks (CNNs):
0:52

if you're struggling on where to start learning ML, here’s a playlist of 30 youtube videos to learn machine learning fundamentals from scratch "Machine Learning: Teach by Doing" is a solid choice to learn both theory and code. (1) Introduction to Machine Learning Teach by Doing: (2) What is Machine Learning? History of Machine Learning: (3) Types of ML Models: (4) 6 steps of any ML project: (5) Install Python and VSCode and run your first code: (6) Linear Classifiers Part 1: (7) Linear Classifiers Part 2: (8) Jupyter Notebook, Numpy and Scikit-Learn: (9) Running the Random Linear Classifier Algorithm in Python: (10) The oldest ML model - Perceptron: (11) Coding the Perceptron: (12) Perceptron Convergence Theorem: (13) Magic of features in Machine Learning: (14) One hot encoding: (15) Logistic Regression Part 1: (16) Cross Entropy Loss: (17) How gradient descent works: (18) Logistic Regression from scratch in Python: (19) Introduction to Regularization: (20) Implementing Regularization in Python: (21) Linear Regression Introduction: (22) Ordinary Least Squares step by step implementation: (23) Ridge regression fundamentals and intuition: (24) Regression recap for interviews: (25) Neural network architecture in 30 minutes: (26) Backpropagation intuition: (27) Neural network activation functions: (28) Momentum in gradient descent: (29) Hands on neural network training in Python: (30) Introduction to Convolutional Neural Networks (CNNs):

ℏεsam

109,292 views • 1 year ago

We built a Spiking Neural Network (SNN) to fully control a physical robot arm (6-DOF), and it's running entirely on a Raspberry Pi (no HAT). In our approach, the SNN starts untrained and drives the servos directly, learning in real time through local learning rules (no backprop or gradient descent). The goal with Twitch-y (the robot + SNN brain) is to let it explore and build an understanding of its own body until it can touch the plate on the mat, while also validating the SNN architecture and some of the math. In the video: - Top right: the SNN architecture - Bottom right: the mini-brain spiking in real time while controlling the arm - Left: Twitch-y (Hugging Face SO-101) If you want to learn more about Artificial Brains, come visit us this Friday (13th), at Founders Inc 👉
0:29

We built a Spiking Neural Network (SNN) to fully control a physical robot arm (6-DOF), and it's running entirely on a Raspberry Pi (no HAT). In our approach, the SNN starts untrained and drives the servos directly, learning in real time through local learning rules (no backprop or gradient descent). The goal with Twitch-y (the robot + SNN brain) is to let it explore and build an understanding of its own body until it can touch the plate on the mat, while also validating the SNN architecture and some of the math. In the video: - Top right: the SNN architecture - Bottom right: the mini-brain spiking in real time while controlling the arm - Left: Twitch-y (Hugging Face SO-101) If you want to learn more about Artificial Brains, come visit us this Friday (13th), at Founders Inc 👉

Alexander A. Wolf

30,367 views • 6 months ago

There's a profound elegance in watching gradient descent find the signal in the noise. This is a simple MLP with sigmoid activations slowly warping to approximate f(x) = 1/(1 + x²). Watch the loss curve right around epoch 400. That sudden phase transition where the network finally "gets it" and snaps into the Witch of Agnesi shape is incredibly satisfying to watch.
0:20

There's a profound elegance in watching gradient descent find the signal in the noise. This is a simple MLP with sigmoid activations slowly warping to approximate f(x) = 1/(1 + x²). Watch the loss curve right around epoch 400. That sudden phase transition where the network finally "gets it" and snaps into the Witch of Agnesi shape is incredibly satisfying to watch.

Mathematica

78,616 views • 3 months ago

As someone who trains LLMs, this 20-minute gradient descent video is the closest thing to a "why the memorization vs generalization debate matters" explainer I've ever seen released for free. Everyone thinks neural nets learn features. They often just memorize. The video walks through the 2017 paper that shocked the field: shuffle your labels randomly and modern networks will still fit them perfectly. 25 minutes. Bookmark & watch today.
19:53

As someone who trains LLMs, this 20-minute gradient descent video is the closest thing to a "why the memorization vs generalization debate matters" explainer I've ever seen released for free. Everyone thinks neural nets learn features. They often just memorize. The video walks through the 2017 paper that shocked the field: shuffle your labels randomly and modern networks will still fit them perfectly. 25 minutes. Bookmark & watch today.

fintex

15,835 views • 6 days ago

🚨 BREAKING: Trevv allegedly snatches ChudTheBuilder the Builder’s hat LIVE on #PumpFun stream 😭 🎩 Absolute chaos breaking out in the trenches right now as viewers watch the hat heist unfold in real time. Clip below of live stream mins ago
2:38

🚨 BREAKING: Trevv allegedly snatches ChudTheBuilder the Builder’s hat LIVE on #PumpFun stream 😭 🎩 Absolute chaos breaking out in the trenches right now as viewers watch the hat heist unfold in real time. Clip below of live stream mins ago

Web3livenews

2,760,473 views • 3 months ago

$LAIKA - THE DOGE L2 NATIVE TOKEN IS LIVE 🙌 Laïka is a layer built for true believers in Dogecoin’s vision, designed to unlock its potential beyond just being a meme. $LAIKA CA (ETH Network): 0x19E1F2f837a3b90EBd0730cb6111189Be0E1b6D6 $LAIKA CA (LAIKA Network): 0x4200000000000000000000000000000000000000 The first Dogecoin Layer 2 is about to make history.
0:29

$LAIKA - THE DOGE L2 NATIVE TOKEN IS LIVE 🙌 Laïka is a layer built for true believers in Dogecoin’s vision, designed to unlock its potential beyond just being a meme. $LAIKA CA (ETH Network): 0x19E1F2f837a3b90EBd0730cb6111189Be0E1b6D6 $LAIKA CA (LAIKA Network): 0x4200000000000000000000000000000000000000 The first Dogecoin Layer 2 is about to make history.

Laika - Doge Super App

182,621 views • 1 year ago

LMFAOOOOOO 🚨 my friend Trevv ($NIGGA) allegedly snatches ChudTheBuilder the Builder’s hat LIVE on $pump stream 😭 🎩 Absolute chaos breaking out in the trenches right now as viewers watch the hat heist unfold in real time. $chud
1:13

LMFAOOOOOO 🚨 my friend Trevv ($NIGGA) allegedly snatches ChudTheBuilder the Builder’s hat LIVE on $pump stream 😭 🎩 Absolute chaos breaking out in the trenches right now as viewers watch the hat heist unfold in real time. $chud

Tommy B. 🇺🇸

65,967 views • 3 months ago

Panda chaos at its finest! From hand-holding with keepers to sledding in a red boat, rolling in snow, and hanging upside down like a furry acrobat — this might be the most entertainin fun you’ll watch today! Real pandas, zero AI. Just pure goofy greatness. Watch till the end 👀
1:07

Panda chaos at its finest! From hand-holding with keepers to sledding in a red boat, rolling in snow, and hanging upside down like a furry acrobat — this might be the most entertainin fun you’ll watch today! Real pandas, zero AI. Just pure goofy greatness. Watch till the end 👀

Jan

21,626 views • 3 months ago

Inspired by Andrej Karpathy's practice of tinkering with smaller GPTs to gain intuition, I've been training small neural nets to play this simple 2d game I created. On the left is a visualization of the neural net firing in real time. Built with Claude, Three.js, and WebGPU and using JAX from Google DeepMind. I’m piping the neuron activation into Ableton as MIDI to trigger Serum 2.
0:21

Inspired by Andrej Karpathy's practice of tinkering with smaller GPTs to gain intuition, I've been training small neural nets to play this simple 2d game I created. On the left is a visualization of the neural net firing in real time. Built with Claude, Three.js, and WebGPU and using JAX from Google DeepMind. I’m piping the neuron activation into Ableton as MIDI to trigger Serum 2.

Aaron Lemke

22,687 views • 3 months ago

IS THIS THE SICKEST HAND IN TV POKER HISTORY?!?! Bill Perkins (Guy) goes ALL-IN, but he's late for a flight. So he leaves the table and leaves HANDZ to make a decision for over $500,000 😮 Bill watched in real time at the airport to see if he won Watch live:
8:02

IS THIS THE SICKEST HAND IN TV POKER HISTORY?!?! Bill Perkins (Guy) goes ALL-IN, but he's late for a flight. So he leaves the table and leaves HANDZ to make a decision for over $500,000 😮 Bill watched in real time at the airport to see if he won Watch live:

Lodge Card Club

397,644 views • 3 years ago

FOMC volatility is coming fast. Chris Guzman (KickStart Trading Ltd) )returns to TTB and goes live straight after the Fed decision to trade the move in real time. Gary Fichardt vs KickStart Trading Ltd | Hosted by TraderNick Sponsored by DNAFunded with vouchers to win live.
0:30

FOMC volatility is coming fast. Chris Guzman (KickStart Trading Ltd) )returns to TTB and goes live straight after the Fed decision to trade the move in real time. Gary Fichardt vs KickStart Trading Ltd | Hosted by TraderNick Sponsored by DNAFunded with vouchers to win live.

The Trading Battle

48,726 views • 6 months ago

A rare, heartwarming moment from classic television history ✨ In this unforgettable 1965 clip, John Wayne unexpectedly joins Dean Martin during a live performance on The Dean Martin Show — right in the middle of Dean’s hit song Everybody Loves Somebody. Pure spontaneity. Old-school charm. And a moment that perfectly captures the magic of live television. ✨🎙️
0:57

A rare, heartwarming moment from classic television history ✨ In this unforgettable 1965 clip, John Wayne unexpectedly joins Dean Martin during a live performance on The Dean Martin Show — right in the middle of Dean’s hit song Everybody Loves Somebody. Pure spontaneity. Old-school charm. And a moment that perfectly captures the magic of live television. ✨🎙️

🌸🎵 Beautiful Melody 🎶💖

72,904 views • 5 months ago

Backpropagation by hand ✍️ ~ 11 steps walkthrough below Backpropagation is the algorithm that actually trains a neural network, and it is where most people stop following along. It is not calculus you cannot do. It is matrix multiplication, working backward, one layer at a time. So I drew and calculated one entirely by hand. Goal: push the loss gradient back through a 3-layer network and land on a new value for every weight and bias. = 1. Given = A 3-layer perceptron, an input X, predictions Ypred = [0.5, 0.5, 0], and the truth Ytarget = [0, 1, 0]. = 2. Backprop gradient cells = Let us draw empty cells for every gradient we are about to compute. The shape of the answer comes first. = 3. Layer 3 softmax = We get dL/dz3 straight from Ypred minus Ytarget = [0.5, -0.5, 0]. No chain rule needed, and that shortcut is the whole reason softmax and cross-entropy are paired. = 4. Layer 3 weights and biases = Let us multiply dL/dz3 by [a2 | 1]. One multiplication gives the gradient for W3 and b3 together. = 5. Layer 2 activations = We multiply dL/dz3 by W3 to get dL/da2. The gradient moves back across a layer the same way the signal moved forward. = 6. Layer 2 ReLU = Let us pass it through the gate: keep the gradient where the activation was positive, zero it everywhere else. = 7. Layer 2 weights and biases = We multiply dL/dz2 by [a1 | 1]. The same figure as step 4, one layer up. = 8. Layer 1 activations = Let us multiply dL/dz2 by W2. = 9. Layer 1 ReLU = We apply the same gate again, now on a1. = 10. Layer 1 weights and biases = Let us multiply dL/dz1 by [x | 1], and every weight in the network now has a gradient. = 11. Update = We subtract, and the network has learned. In practice a learning rate scales this step. The gradients: dL/dz3 = [0.5, -0.5, 0] dL/da1 = [1, -2, 2, -1] dL/dz1 = [0, -2, 2, -1] The takeaway: matrix multiplication is all you need. Just like the forward pass, backpropagation is matrix multiplications end to end. You can do every one by hand, slowly and imperfectly, which is exactly why a GPU's ability to do them fast mattered so much to deep learning. 💾 Save this post!
0:26

Backpropagation by hand ✍️ ~ 11 steps walkthrough below Backpropagation is the algorithm that actually trains a neural network, and it is where most people stop following along. It is not calculus you cannot do. It is matrix multiplication, working backward, one layer at a time. So I drew and calculated one entirely by hand. Goal: push the loss gradient back through a 3-layer network and land on a new value for every weight and bias. = 1. Given = A 3-layer perceptron, an input X, predictions Ypred = [0.5, 0.5, 0], and the truth Ytarget = [0, 1, 0]. = 2. Backprop gradient cells = Let us draw empty cells for every gradient we are about to compute. The shape of the answer comes first. = 3. Layer 3 softmax = We get dL/dz3 straight from Ypred minus Ytarget = [0.5, -0.5, 0]. No chain rule needed, and that shortcut is the whole reason softmax and cross-entropy are paired. = 4. Layer 3 weights and biases = Let us multiply dL/dz3 by [a2 | 1]. One multiplication gives the gradient for W3 and b3 together. = 5. Layer 2 activations = We multiply dL/dz3 by W3 to get dL/da2. The gradient moves back across a layer the same way the signal moved forward. = 6. Layer 2 ReLU = Let us pass it through the gate: keep the gradient where the activation was positive, zero it everywhere else. = 7. Layer 2 weights and biases = We multiply dL/dz2 by [a1 | 1]. The same figure as step 4, one layer up. = 8. Layer 1 activations = Let us multiply dL/dz2 by W2. = 9. Layer 1 ReLU = We apply the same gate again, now on a1. = 10. Layer 1 weights and biases = Let us multiply dL/dz1 by [x | 1], and every weight in the network now has a gradient. = 11. Update = We subtract, and the network has learned. In practice a learning rate scales this step. The gradients: dL/dz3 = [0.5, -0.5, 0] dL/da1 = [1, -2, 2, -1] dL/dz1 = [0, -2, 2, -1] The takeaway: matrix multiplication is all you need. Just like the forward pass, backpropagation is matrix multiplications end to end. You can do every one by hand, slowly and imperfectly, which is exactly why a GPU's ability to do them fast mattered so much to deep learning. 💾 Save this post!

Tom Yeh

955,833 views • 19 days ago

Ever wondered what’s happening inside an AI’s “brain”? This is a neural network in action, taking raw data and transforming it into decisions through thousands of layered calculations. Each layer extracts patterns, refines signals, and passes smarter information forward, slowly turning noise into meaning. It’s not thinking like a human but it is learning, adapting, and improving with every pass. What looks like chaos is actually pure math shaping intelligence in real time
0:35

Ever wondered what’s happening inside an AI’s “brain”? This is a neural network in action, taking raw data and transforming it into decisions through thousands of layered calculations. Each layer extracts patterns, refines signals, and passes smarter information forward, slowly turning noise into meaning. It’s not thinking like a human but it is learning, adapting, and improving with every pass. What looks like chaos is actually pure math shaping intelligence in real time

Kekius Maximus

37,481 views • 6 months ago

Of note in the SMU opener now on ACC Network: this is the first game to feature live audio from The ACC Game Day Operations Center in Charlotte. ACCN lets fans listen to real-time conversations of reviewable plays - a first of its kind in college football coverage.
1:54

Of note in the SMU opener now on ACC Network: this is the first game to feature live audio from The ACC Game Day Operations Center in Charlotte. ACCN lets fans listen to real-time conversations of reviewable plays - a first of its kind in college football coverage.

bill hofheimer

94,323 views • 11 months ago