Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Google's first rule for machine learning: don't use machine learning. A 3-line PID equation beats a neural network at balancing a robot. Proportional error, integral of accumulated error, derivative of error change rate - three terms, hand-tuned gains, no training data. The same control theory running inside every GPU...

0xEronn's profile picture

Eron

10,580 subscribers

29,627 Aufrufe • vor 2 Tagen •via X (Twitter)

Wissenschaft & TechnologieBildung
LIVE

Anya Rossi• Live Now

Private livecam show

3 Kommentare

Profilbild von hiroko watanabe
hiroko watanabevor 1 Tag

@0xEronn Great Video, indeed. Very interesting and understandable, not easy of course, but quite helpful to learn physics.

Profilbild von Emmanuel Nwachukwu 💙🥶
Emmanuel Nwachukwu 💙🥶vor 1 Tag

Good reminder that a simple rule can beat a complex model. As a beginner I like seeing the basics get respect before the fancy stuff.

Profilbild von The Chieftain A
The Chieftain Avor 1 Tag

Great video

Ähnliche Videos

Ever wondered what neural networks are and how they work? Systems like ChatGPT use neural networks to work as well as they do. Neural networks are composed of "layers" of neurons, layers with different functions; connections between layers called "weights"; and mathematical functions called "activation functions". If you’re interested in learning about these systems, check the comments. Ultimately, the neural network structure of the model serves to visually demonstrate that it is, in fact, a complex mathematical equation. When companies release the model's weights, they are releasing a key component needed to run the model's complete equation. Without the weights, the equation is incomplete. For the math-minded: the weights of a model are the learned numbers (they are variables during training) that are then used as constants in the mathematical functions that make up the model. Neural networks are ultimately just one big, hyper-complex mathematical function, and when a model is trained, it learns the constants associated with the high-dimensional input.
2:37

Ever wondered what neural networks are and how they work? Systems like ChatGPT use neural networks to work as well as they do. Neural networks are composed of "layers" of neurons, layers with different functions; connections between layers called "weights"; and mathematical functions called "activation functions". If you’re interested in learning about these systems, check the comments. Ultimately, the neural network structure of the model serves to visually demonstrate that it is, in fact, a complex mathematical equation. When companies release the model's weights, they are releasing a key component needed to run the model's complete equation. Without the weights, the equation is incomplete. For the math-minded: the weights of a model are the learned numbers (they are variables during training) that are then used as constants in the mathematical functions that make up the model. Neural networks are ultimately just one big, hyper-complex mathematical function, and when a model is trained, it learns the constants associated with the high-dimensional input.

Harper Carroll

50,905 Aufrufe • vor 1 Jahr

Every fundamental law of physics - Newton, Einstein, Quantum Field Theory - is derived from a single equation. Physicists don't propose new laws by writing forces anymore. They write a new Lagrangian and the math produces the physics automatically. The same principle that governs a swinging pendulum governs every quantum field in the universe - and the optimizer inside every LLM training run is solving the same underlying problem. The mechanism is stationary action. A system takes the path where the total action stops changing for any small variation. That condition produces the Euler-Lagrange equation. One equation, any number of variables, any theory of physics. In Quantum Field Theory the variables are fields across all of space and the gradient must vanish at every point simultaneously - exactly the convergence condition gradient descent hunts for across billions of LLM parameters during backpropagation. 20 minutes. Bookmark & watch today. The single equation that every law of physics is secretly a special case of.
18:21

Every fundamental law of physics - Newton, Einstein, Quantum Field Theory - is derived from a single equation. Physicists don't propose new laws by writing forces anymore. They write a new Lagrangian and the math produces the physics automatically. The same principle that governs a swinging pendulum governs every quantum field in the universe - and the optimizer inside every LLM training run is solving the same underlying problem. The mechanism is stationary action. A system takes the path where the total action stops changing for any small variation. That condition produces the Euler-Lagrange equation. One equation, any number of variables, any theory of physics. In Quantum Field Theory the variables are fields across all of space and the gradient must vanish at every point simultaneously - exactly the convergence condition gradient descent hunts for across billions of LLM parameters during backpropagation. 20 minutes. Bookmark & watch today. The single equation that every law of physics is secretly a special case of.

Eron

24,186 Aufrufe • vor 24 Tagen

Lyapunov proved in 1892 that you never need to solve a differential equation to know if a system will stabilize. Find one function that behaves like energy — positive everywhere, zero at equilibrium — and if it's always decreasing, the system is guaranteed to converge. No solution required. The trick is that real energy often fails the test. A pendulum's kinetic energy hits zero at every moment of stillness, not just at rest — so it can't prove asymptotic stability alone. You need a generalized artificial energy with cross terms mixing position and velocity. The same Lyapunov stability analysis is what ML engineers run on neural network training dynamics to prove gradient descent actually converges instead of oscillating forever on GPU clusters. 16 minutes. Bookmark & watch today.
15:54

Lyapunov proved in 1892 that you never need to solve a differential equation to know if a system will stabilize. Find one function that behaves like energy — positive everywhere, zero at equilibrium — and if it's always decreasing, the system is guaranteed to converge. No solution required. The trick is that real energy often fails the test. A pendulum's kinetic energy hits zero at every moment of stillness, not just at rest — so it can't prove asymptotic stability alone. You need a generalized artificial energy with cross terms mixing position and velocity. The same Lyapunov stability analysis is what ML engineers run on neural network training dynamics to prove gradient descent actually converges instead of oscillating forever on GPU clusters. 16 minutes. Bookmark & watch today.

Deliriumm

46,282 Aufrufe • vor 1 Monat

Does GPT understand the world? Here is what Ilya Sutskever, co-founder of OpenAI, says during a discussion with Jensen Huang, CEO of Nvidia: (1) When we train a large neural network to accurately predict the next word in lots of different texts from the internet, the AI is learning a world model. (2) On the surface, it may look like learning correlations in text, but it turns out that to 'just learn' statistical correlations in text, to compress information really well, what the neural network learns is some representation of the process that produced the text. (3) This text is a projection of the world...what the neural network is learning is aspects of the world, of people, of the human conditions, their hopes, dreams, motivations, their interactions...the situations we are in. The neural network learns a compressed, abstract, usable representation." Do you think learning representations = understanding? Are large language models simply stochastic parrots, or are they much more?
3:10

Does GPT understand the world? Here is what Ilya Sutskever, co-founder of OpenAI, says during a discussion with Jensen Huang, CEO of Nvidia: (1) When we train a large neural network to accurately predict the next word in lots of different texts from the internet, the AI is learning a world model. (2) On the surface, it may look like learning correlations in text, but it turns out that to 'just learn' statistical correlations in text, to compress information really well, what the neural network learns is some representation of the process that produced the text. (3) This text is a projection of the world...what the neural network is learning is aspects of the world, of people, of the human conditions, their hopes, dreams, motivations, their interactions...the situations we are in. The neural network learns a compressed, abstract, usable representation." Do you think learning representations = understanding? Are large language models simply stochastic parrots, or are they much more?

Alex Ker 🔭

1,367,231 Aufrufe • vor 3 Jahren

A lot of robot learning pipelines treat embodiment mismatch as a software problem. Collect data with one device, retarget the motion to another robot, and try to deal with the differences later. TwinDEX flips that idea around. This system is from a Chinese robotics company called X Square. Instead of starting with a generic data-collection device, the team co-designs a wearable three-finger end-effector and a robotic hand as two sides of the same learning system. They align the things that actually matter during manipulation: joint structure, link proportions, contact geometry, surface properties, visual appearance, sensing, and timing. That matters because dexterous manipulation is much more than matching hand poses. A few millimeters of contact error or a different force relationship can completely change how a task is executed. In the collection evaluation, TwinDEX delivered up to 5.3 times the effective throughput of on-robot teleoperation. It’s a useful reminder that scaling robot learning may not only be about bigger models and more data. Sometimes the hardware collecting the data is part of the data problem itself.
0:20

A lot of robot learning pipelines treat embodiment mismatch as a software problem. Collect data with one device, retarget the motion to another robot, and try to deal with the differences later. TwinDEX flips that idea around. This system is from a Chinese robotics company called X Square. Instead of starting with a generic data-collection device, the team co-designs a wearable three-finger end-effector and a robotic hand as two sides of the same learning system. They align the things that actually matter during manipulation: joint structure, link proportions, contact geometry, surface properties, visual appearance, sensing, and timing. That matters because dexterous manipulation is much more than matching hand poses. A few millimeters of contact error or a different force relationship can completely change how a task is executed. In the collection evaluation, TwinDEX delivered up to 5.3 times the effective throughput of on-robot teleoperation. It’s a useful reminder that scaling robot learning may not only be about bigger models and more data. Sometimes the hardware collecting the data is part of the data problem itself.

Alamin

48,112 Aufrufe • vor 2 Monaten

A Neural Network Can Grow New Neurons Where It Is Confused? In 1994, Bernd Fritzke published A Growing Neural Gas Network Learns Topologies. He introduced a network that starts small, follows incoming data, and inserts new neurons where its error is highest. In the animation, the fog is the drifting data. The glowing nodes are neurons. The fibers are learned connections. The network grows into a living skeleton of the manifold.
0:30

A Neural Network Can Grow New Neurons Where It Is Confused? In 1994, Bernd Fritzke published A Growing Neural Gas Network Learns Topologies. He introduced a network that starts small, follows incoming data, and inserts new neurons where its error is highest. In the animation, the fog is the drifting data. The glowing nodes are neurons. The fibers are learned connections. The network grows into a living skeleton of the manifold.

Mathelirium

38,431 Aufrufe • vor 5 Monaten

Reinforcement learning is used to speed the production of behavior for the Boston Dynamics Atlas humanoid robot. At the heart of the learning process is a physics-based simulator that generates training data for a variety of maneuvers.
1:10

Reinforcement learning is used to speed the production of behavior for the Boston Dynamics Atlas humanoid robot. At the heart of the learning process is a physics-based simulator that generates training data for a variety of maneuvers.

RAI Institute

76,771 Aufrufe • vor 1 Jahr

Created a WebGL neural network visualization for the quadruped robot I've been working on. The more red, the higher the activation. Bluer is less activation, while green is a midpoint.
0:37

Created a WebGL neural network visualization for the quadruped robot I've been working on. The more red, the higher the activation. Bluer is less activation, while green is a midpoint.

Brandon

195,804 Aufrufe • vor 3 Jahren

A 91-year-old professor is why Nvidia is worth $4 trillion. His name is Gilbert Strang. He teaches linear algebra at MIT. Every AI model on Earth runs on his course. The course has been free on YouTube since 2005. The videos have earned him nothing. MIT 18.06 opens with "The Geometry of Linear Equations." No advanced math. Strang takes a system of two equations, draws it two ways, and shows the class that a matrix is a picture, not an abstraction. The row picture is two lines that cross. The column picture is two arrows that sum to a target. Every neural network on Earth operates on the column picture. Strang first taught linear algebra at MIT in 1962. He wrote the textbook in 1976. It is on every serious engineer's shelf. Every quant fund, every ML lab, every rendering engine at Pixar is running his math. His central insight is that most people are taught matrices as bookkeeping. That is the first thing to unlearn. A matrix is a linear transformation. A linear transformation is a way of moving space. Once you see the space move, the math stops being algebra and becomes geometry. The Kalman filter is a linear system. PCA is a linear system. Every gradient step in a neural net is a matrix-vector product. GPT is a stack of matrix-vector products, each one a scene from MIT 18.06 running on a Blackwell GPU. He retired in 2023 after 61 years at MIT. The course is still up. Watched tens of millions of times. The chip is $40,000. Strang never asked for a royalty.
37:24

A 91-year-old professor is why Nvidia is worth $4 trillion. His name is Gilbert Strang. He teaches linear algebra at MIT. Every AI model on Earth runs on his course. The course has been free on YouTube since 2005. The videos have earned him nothing. MIT 18.06 opens with "The Geometry of Linear Equations." No advanced math. Strang takes a system of two equations, draws it two ways, and shows the class that a matrix is a picture, not an abstraction. The row picture is two lines that cross. The column picture is two arrows that sum to a target. Every neural network on Earth operates on the column picture. Strang first taught linear algebra at MIT in 1962. He wrote the textbook in 1976. It is on every serious engineer's shelf. Every quant fund, every ML lab, every rendering engine at Pixar is running his math. His central insight is that most people are taught matrices as bookkeeping. That is the first thing to unlearn. A matrix is a linear transformation. A linear transformation is a way of moving space. Once you see the space move, the math stops being algebra and becomes geometry. The Kalman filter is a linear system. PCA is a linear system. Every gradient step in a neural net is a matrix-vector product. GPT is a stack of matrix-vector products, each one a scene from MIT 18.06 running on a Blackwell GPU. He retired in 2023 after 61 years at MIT. The course is still up. Watched tens of millions of times. The chip is $40,000. Strang never asked for a royalty.

Ochob

131,686 Aufrufe • vor 3 Monaten

A humanoid robot just unloaded a dishwasher for 67 hours straight. By end of 2026, the same robot will perform surgery. That's not a prediction from a sci-fi writer. That's Brett Adcock. CEO of Figure AI. Said it on camera this month. Here's what makes this insane. Two years ago Figure's robot put a Keurig cup in a coffee maker. That was the breakthrough moment. The whole team celebrated. A coffee cup. Today that same robot runs 67 consecutive hours in a BMW factory. Grabbing packages. Finding barcodes. Placing them. One operation every second. Just a neural network that learned by watching. And Brett just said the hands that do that the same fingers, the same sensors, the same neural net are already capable of surgical precision from a hardware standpoint. "From a hardware perspective in 2026 we'll be able to do what surgeons can do." The AI just has to catch up to the hands. Two years ago: a coffee cup. This year: a factory. Next: the operating table. The robot didn't change, the learning did and it's not stopping.
1:43:47

A humanoid robot just unloaded a dishwasher for 67 hours straight. By end of 2026, the same robot will perform surgery. That's not a prediction from a sci-fi writer. That's Brett Adcock. CEO of Figure AI. Said it on camera this month. Here's what makes this insane. Two years ago Figure's robot put a Keurig cup in a coffee maker. That was the breakthrough moment. The whole team celebrated. A coffee cup. Today that same robot runs 67 consecutive hours in a BMW factory. Grabbing packages. Finding barcodes. Placing them. One operation every second. Just a neural network that learned by watching. And Brett just said the hands that do that the same fingers, the same sensors, the same neural net are already capable of surgical precision from a hardware standpoint. "From a hardware perspective in 2026 we'll be able to do what surgeons can do." The AI just has to catch up to the hands. Two years ago: a coffee cup. This year: a factory. Next: the operating table. The robot didn't change, the learning did and it's not stopping.

Shruti

47,962 Aufrufe • vor 6 Monaten

Backpropagation in Machine Learning In 1970, a Finnish master's student named Seppo Linnainmaa wrote a thesis on tracing a computer's tiny rounding errors backwards through a long calculation, one step at a time. Sixteen years later, David Rumelhart, Geoffrey Hinton and Ronald Williams showed that the same backward trick lets a Neural Network work out how to fix every one of its connections at once, and the world called it 'Backpropagation'. Every big AI model today still learns by passing its mistakes backwards in exactly this way.
0:30

Backpropagation in Machine Learning In 1970, a Finnish master's student named Seppo Linnainmaa wrote a thesis on tracing a computer's tiny rounding errors backwards through a long calculation, one step at a time. Sixteen years later, David Rumelhart, Geoffrey Hinton and Ronald Williams showed that the same backward trick lets a Neural Network work out how to fix every one of its connections at once, and the world called it 'Backpropagation'. Every big AI model today still learns by passing its mistakes backwards in exactly this way.

Mathelirium

13,116 Aufrufe • vor 4 Tagen

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

109,764 Aufrufe • vor 1 Jahr

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

117,748 Aufrufe • vor 1 Jahr

Watch Spot crouch, jump, climb boxes and leap across gaps, controlled by a neural network trained with reinforcement learning (RL) and multi-expert distillation. Multiple expert policies were trained and distilled together into a single policy that was fine tuned to improve performance over diverse terrains. This work was inspired by ANYmal’s parkour capabilities. The neural network processes depth data from Spot's sensors to construct an understanding of the environment.
0:48

Watch Spot crouch, jump, climb boxes and leap across gaps, controlled by a neural network trained with reinforcement learning (RL) and multi-expert distillation. Multiple expert policies were trained and distilled together into a single policy that was fine tuned to improve performance over diverse terrains. This work was inspired by ANYmal’s parkour capabilities. The neural network processes depth data from Spot's sensors to construct an understanding of the environment.

RAI Institute

15,057 Aufrufe • vor 5 Monaten

Ten million people have watched an MIT professor teach a course whose first lecture is literally titled "What is a Derivative?" Almost none have written down the two-line answer. He filmed the lecture once in the fall of 2007 and it has been on YouTube ever since. Math tutors charge $200 an hour to teach a diluted version of what he covered in 50 minutes for free. His name is David Jerison. He is a professor of mathematics at MIT and the instructor of 18.01 Single Variable Calculus, one of the most-watched math courses in the history of the internet. The 50-minute clip in this video is Lecture 1, filmed at MIT in the fall of 2007. Jerison is deriving the definition of a derivative from a single tangent line. The whole framework fits on a napkin. A derivative is just how much y changes when x moves a tiny bit. Draw a tangent line to any curve at any point. The slope of that line is the derivative. Memorize one formula, the power rule, and you can differentiate every polynomial on earth in your head. Chain that with a handful of exceptions and you can differentiate almost every function humanity has ever written down. That single set of rules is what every neural network runs on gradient descent, what every rocket landing at SpaceX solves in real time, and what every options desk at Goldman Sachs is running behind every quote you see on the screen. "In mathematics you don't understand things. You just get used to them." That is John von Neumann, the mathematician who helped design the atomic bomb and invent the modern computer. Jerison returns to the same idea in every lecture. Almost no student giving up on calculus has heard von Neumann say it out loud. Every quant fund on Wall Street pays entry-level analysts $250,000 to know the same power rule Jerison derives on the board. Every AI bootcamp charges tens of thousands to teach a diluted version of the same equation on a laptop. The lecture is free on MIT OpenCourseWare. The textbook is under sixty dollars. Almost none of the millions who watched have ever taken the power rule and applied it to their own numbers on their own paper. The math is free. The willingness to actually take one derivative before your next model, trade, or engineering trade-off is the entire edge.
50:48

Ten million people have watched an MIT professor teach a course whose first lecture is literally titled "What is a Derivative?" Almost none have written down the two-line answer. He filmed the lecture once in the fall of 2007 and it has been on YouTube ever since. Math tutors charge $200 an hour to teach a diluted version of what he covered in 50 minutes for free. His name is David Jerison. He is a professor of mathematics at MIT and the instructor of 18.01 Single Variable Calculus, one of the most-watched math courses in the history of the internet. The 50-minute clip in this video is Lecture 1, filmed at MIT in the fall of 2007. Jerison is deriving the definition of a derivative from a single tangent line. The whole framework fits on a napkin. A derivative is just how much y changes when x moves a tiny bit. Draw a tangent line to any curve at any point. The slope of that line is the derivative. Memorize one formula, the power rule, and you can differentiate every polynomial on earth in your head. Chain that with a handful of exceptions and you can differentiate almost every function humanity has ever written down. That single set of rules is what every neural network runs on gradient descent, what every rocket landing at SpaceX solves in real time, and what every options desk at Goldman Sachs is running behind every quote you see on the screen. "In mathematics you don't understand things. You just get used to them." That is John von Neumann, the mathematician who helped design the atomic bomb and invent the modern computer. Jerison returns to the same idea in every lecture. Almost no student giving up on calculus has heard von Neumann say it out loud. Every quant fund on Wall Street pays entry-level analysts $250,000 to know the same power rule Jerison derives on the board. Every AI bootcamp charges tens of thousands to teach a diluted version of the same equation on a laptop. The lecture is free on MIT OpenCourseWare. The textbook is under sixty dollars. Almost none of the millions who watched have ever taken the power rule and applied it to their own numbers on their own paper. The math is free. The willingness to actually take one derivative before your next model, trade, or engineering trade-off is the entire edge.

Lumen

31,497 Aufrufe • vor 1 Monat

Since Newton, every law of physics has been written as a differential equation. The same math that describes a pendulum swinging is what makes AI training unstable when learning rates are too large. Differential equations are hard not because the concepts are complex, but because most of them simply cannot be solved exactly. This video shows why - and how phase space diagrams let you understand them anyway without solving anything. 25 minutes. Bookmark & watch today. The chaos theory connection at the end alone is worth it.
27:11

Since Newton, every law of physics has been written as a differential equation. The same math that describes a pendulum swinging is what makes AI training unstable when learning rates are too large. Differential equations are hard not because the concepts are complex, but because most of them simply cannot be solved exactly. This video shows why - and how phase space diagrams let you understand them anyway without solving anything. 25 minutes. Bookmark & watch today. The chaos theory connection at the end alone is worth it.

Eron

26,204 Aufrufe • vor 3 Monaten

Neural networks sometimes memorize training data perfectly for thousands of steps - then suddenly generalize. Physicists call this a phase transition. The same math that explains why water freezes explains why an LLM stops cheating and starts understanding. The key is weight decay acting like pressure on a thermodynamic system. Memorization requires large, fragile weights. A real rule requires smaller, more structured ones. As training continues, the balance shifts until the rule-based solution becomes cheaper to maintain - and the model snaps into it. 14 minutes. Bookmark & watch today. The physics behind the most mysterious thing AI does.
17:24

Neural networks sometimes memorize training data perfectly for thousands of steps - then suddenly generalize. Physicists call this a phase transition. The same math that explains why water freezes explains why an LLM stops cheating and starts understanding. The key is weight decay acting like pressure on a thermodynamic system. Memorization requires large, fragile weights. A real rule requires smaller, more structured ones. As training continues, the balance shifts until the rule-based solution becomes cheaper to maintain - and the model snaps into it. 14 minutes. Bookmark & watch today. The physics behind the most mysterious thing AI does.

Eron

26,222 Aufrufe • vor 2 Monaten

MIT FILMED THE LECTURE WHERE THEIR MOST LEGENDARY LINEAR ALGEBRA PROFESSOR EXPLAINS WHY EVERY GPS SIGNAL EVERY MEDICAL SCAN AND EVERY AI MODEL ON EARTH IS SECRETLY SOLVING A PROBLEM THAT HAS NO SOLUTION This is Gilbert Strang, MIT, 18.06 Linear Algebra, lecture 15. The professor whose textbooks sit in over 3,000 universities across 135 countries and whose course has been watched by millions of engineers and mathematicians worldwide. He opens with one claim - when equations have no solution, you do not give up. You solve the closest problem that can be solved. He starts with a vector b and a line through a. The projection of b onto that line is the point closest to b that actually lives on the line. The key is a right angle. The error - the gap between b and its projection - must be perpendicular to a. That one geometric fact produces the entire formula. The projection is a times a transpose b divided by a transpose a. One fraction. The numerator is a matrix. The denominator is a number. Then the projection matrix. Every projection is carried out by a matrix P that multiplies b and lands on the line. That matrix has two properties that define all projections everywhere. First, P transpose equals P - the matrix is symmetric. Second, P squared equals P - project twice and you stay where you are. The first projection moves you onto the line. The second leaves you there. Then higher dimensions. Instead of projecting onto a line, project onto a plane. Instead of one vector a, you have a matrix A with two columns spanning the plane. The error vector must now be perpendicular to both columns - perpendicular to the entire plane. That condition produces one matrix equation. A transpose times the error equals zero. The error lives in the null space of A transpose, which is exactly perpendicular to the column space of A. The four fundamental subspaces appear without being called. Then the formula for n dimensions. The projection matrix is A times A transpose A inverse times A transpose. Strang warns the room not to simplify it by canceling A inverse against A - A is not square, it has no inverse, and the formula cannot be pulled apart. The only case where it simplifies to the identity is when A spans the whole space and the projection is b itself. Watch the moment he applies the formula to fitting a line through three points that no line can pass through. Three equations, two unknowns, no solution. He writes the matrix, writes the right-hand side, and shows that multiplying both sides by A transpose produces an equation that always has a solution. That equation is the foundation of least squares, GPS triangulation, and every regression model trained in 2026. A data scientist I know rewatched this lecture before building a recommendation system from scratch. Said it was the first time the normal equations felt like geometry rather than a formula someone handed down to memorize. Free on YouTube, MIT OpenCourseWare, filmed over 20 years ago. bookmark this and watch later - after this lecture every unsolvable equation you meet will feel like a projection waiting to be found
48:19

MIT FILMED THE LECTURE WHERE THEIR MOST LEGENDARY LINEAR ALGEBRA PROFESSOR EXPLAINS WHY EVERY GPS SIGNAL EVERY MEDICAL SCAN AND EVERY AI MODEL ON EARTH IS SECRETLY SOLVING A PROBLEM THAT HAS NO SOLUTION This is Gilbert Strang, MIT, 18.06 Linear Algebra, lecture 15. The professor whose textbooks sit in over 3,000 universities across 135 countries and whose course has been watched by millions of engineers and mathematicians worldwide. He opens with one claim - when equations have no solution, you do not give up. You solve the closest problem that can be solved. He starts with a vector b and a line through a. The projection of b onto that line is the point closest to b that actually lives on the line. The key is a right angle. The error - the gap between b and its projection - must be perpendicular to a. That one geometric fact produces the entire formula. The projection is a times a transpose b divided by a transpose a. One fraction. The numerator is a matrix. The denominator is a number. Then the projection matrix. Every projection is carried out by a matrix P that multiplies b and lands on the line. That matrix has two properties that define all projections everywhere. First, P transpose equals P - the matrix is symmetric. Second, P squared equals P - project twice and you stay where you are. The first projection moves you onto the line. The second leaves you there. Then higher dimensions. Instead of projecting onto a line, project onto a plane. Instead of one vector a, you have a matrix A with two columns spanning the plane. The error vector must now be perpendicular to both columns - perpendicular to the entire plane. That condition produces one matrix equation. A transpose times the error equals zero. The error lives in the null space of A transpose, which is exactly perpendicular to the column space of A. The four fundamental subspaces appear without being called. Then the formula for n dimensions. The projection matrix is A times A transpose A inverse times A transpose. Strang warns the room not to simplify it by canceling A inverse against A - A is not square, it has no inverse, and the formula cannot be pulled apart. The only case where it simplifies to the identity is when A spans the whole space and the projection is b itself. Watch the moment he applies the formula to fitting a line through three points that no line can pass through. Three equations, two unknowns, no solution. He writes the matrix, writes the right-hand side, and shows that multiplying both sides by A transpose produces an equation that always has a solution. That equation is the foundation of least squares, GPS triangulation, and every regression model trained in 2026. A data scientist I know rewatched this lecture before building a recommendation system from scratch. Said it was the first time the normal equations felt like geometry rather than a formula someone handed down to memorize. Free on YouTube, MIT OpenCourseWare, filmed over 20 years ago. bookmark this and watch later - after this lecture every unsolvable equation you meet will feel like a projection waiting to be found

Lupen

24,677 Aufrufe • vor 2 Monaten