Загрузка видео...

Не удалось загрузить видео

На главную

We often hear that Machine Learning models learn patterns in data. But what does that look like in geometry? Picture dropping an elastic mesh into a cloud of points and letting it adapt. How would it bend, stretch, and settle so it matches the shape hiding in the data?...

mathelirium's profile picture

Mathelirium

27,621 subscribers

23,021 просмотров • 9 месяцев назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

We often hear that Machine Learning models learn patterns in data. But what does that actually look like in Geometry? If you dropped a little elastic mesh into a cloud of points and let it learn, how would it fold itself to match the shape of the data? In this scene we watch a Self-Organizing Map (SOM), a simple unsupervised neural model, learn the shape of a 3D datasets l, one static and the other dynamic. On top of this, we lay down a square grid of neurons whose weights live in the same plane. At the start, this grid is just a flat net floating across the cloud. It knows nothing about the structure underneath. Learning is a repeated game: Pick a random data point, find the neuron whose weight is closest, and then nudge that neuron and its neighbours toward the point. Do this again and again, while slowly shrinking how far the neighbourhood influence spreads. Python code is available for Subscribers. #MachineLearning #ManifoldLearning #UnsupervisedLearning #NeuralMaps #GeometricML
0:57

We often hear that Machine Learning models learn patterns in data. But what does that actually look like in Geometry? If you dropped a little elastic mesh into a cloud of points and let it learn, how would it fold itself to match the shape of the data? In this scene we watch a Self-Organizing Map (SOM), a simple unsupervised neural model, learn the shape of a 3D datasets l, one static and the other dynamic. On top of this, we lay down a square grid of neurons whose weights live in the same plane. At the start, this grid is just a flat net floating across the cloud. It knows nothing about the structure underneath. Learning is a repeated game: Pick a random data point, find the neuron whose weight is closest, and then nudge that neuron and its neighbours toward the point. Do this again and again, while slowly shrinking how far the neighbourhood influence spreads. Python code is available for Subscribers. #MachineLearning #ManifoldLearning #UnsupervisedLearning #NeuralMaps #GeometricML

Mathelirium

76,377 просмотров • 8 месяцев назад

A neural network can begin as a flat sheet and learn the shape of hidden data A self-organizing map turns learning into geometry. Each data point pulls one winning neuron toward it, but nearby neurons move too, and so the whole lattice bends without losing its neighborhood structure. The strange part is that the network is not given the roll shape. It discovers the shape through competition and local cooperation. Paper: Self-Organized Formation of Topologically Correct Feature Maps Authors: Teuvo Kohonen Year: 1982
0:30

A neural network can begin as a flat sheet and learn the shape of hidden data A self-organizing map turns learning into geometry. Each data point pulls one winning neuron toward it, but nearby neurons move too, and so the whole lattice bends without losing its neighborhood structure. The strange part is that the network is not given the roll shape. It discovers the shape through competition and local cooperation. Paper: Self-Organized Formation of Topologically Correct Feature Maps Authors: Teuvo Kohonen Year: 1982

Mathelirium

133,679 просмотров • 5 месяцев назад

The Machine That Learns The Law Behind The Data A very very interesting US Patent US10963540B2 - Physics Informed Learning Machine describes a learning system that does not begin with data alone. It begins with a physical model, usually written as a differential equation (or PDE) dx/dt = f(x,t) A normal Machine Learning model sees scattered data and tries to fit it. A physics-informed learning machine starts with a law. Then it treats the data as evidence that updates what the model believes about the physical system. For this application, I use the patent idea on NASA C-MAPSS Turbofan engine data. The machine watches multivariate telemetry from a degrading engine and infers a hidden health state that is not measured directly. From that posterior belief, it estimates the engine’s remaining useful life. In the main 3D scene, the engine lifetime is turned into a tunnel. The spiral ribbons are real sensor channels evolving over cycle-time. The glowing core is the inferred health state. The surrounding cloud is uncertainty. The orange wall ahead is the predicted failure horizon. So the big picture is: sensor evidence comes in, posterior belief tightens, and the machine moves from uncertainty toward a concrete failure prediction. The inset posteriors make that explicit. The health posterior shows where the model believes the hidden engine condition sits at the current moment, and how sharply it believes it. The RUL posterior shows the same idea for remaining life... early on it is broad, later it shifts left and narrows as the machine becomes more certain about how close failure is. This idea is not limited to engines. The same idea can apply to data centers, CPUs, GPUs, cooling systems, power grids, robotics, batteries, and any machine that produces telemetry while obeying physical constraints. In an age where machine learning runs on massive hardware infrastructure, this kind of model matters: it can turn noisy sensor streams into early warnings before expensive systems fail.
0:30

The Machine That Learns The Law Behind The Data A very very interesting US Patent US10963540B2 - Physics Informed Learning Machine describes a learning system that does not begin with data alone. It begins with a physical model, usually written as a differential equation (or PDE) dx/dt = f(x,t) A normal Machine Learning model sees scattered data and tries to fit it. A physics-informed learning machine starts with a law. Then it treats the data as evidence that updates what the model believes about the physical system. For this application, I use the patent idea on NASA C-MAPSS Turbofan engine data. The machine watches multivariate telemetry from a degrading engine and infers a hidden health state that is not measured directly. From that posterior belief, it estimates the engine’s remaining useful life. In the main 3D scene, the engine lifetime is turned into a tunnel. The spiral ribbons are real sensor channels evolving over cycle-time. The glowing core is the inferred health state. The surrounding cloud is uncertainty. The orange wall ahead is the predicted failure horizon. So the big picture is: sensor evidence comes in, posterior belief tightens, and the machine moves from uncertainty toward a concrete failure prediction. The inset posteriors make that explicit. The health posterior shows where the model believes the hidden engine condition sits at the current moment, and how sharply it believes it. The RUL posterior shows the same idea for remaining life... early on it is broad, later it shifts left and narrows as the machine becomes more certain about how close failure is. This idea is not limited to engines. The same idea can apply to data centers, CPUs, GPUs, cooling systems, power grids, robotics, batteries, and any machine that produces telemetry while obeying physical constraints. In an age where machine learning runs on massive hardware infrastructure, this kind of model matters: it can turn noisy sensor streams into early warnings before expensive systems fail.

Mathelirium

17,843 просмотров • 5 месяцев назад

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 просмотров • 5 месяцев назад

Paper mesh deformation with pure 2D canvas API. The sheet is built as a grid of points, not as one flat image. Each point keeps its base position, current position, previous position, and a small fake depth value. When I drag one area, the code pulls the nearest point and spreads that force through the grid, so the paper bends instead of just skewing like a card. The structure is held together with constraints between points. Horizontal, vertical, diagonal, and longer links all try to stay close to their original length. That is what gives it paper-like resistance. It can flex, but it does not stretch too far or collapse too much. The solver runs many times per frame, which keeps the shape stable while dragging. The fold detail is driven by texture data. One image is the visible paper surface. Another image is sampled as a fold map: dark values become stronger fold areas, and image gradients give fold direction. That data feeds back into the mesh, so some parts lift more, crease more, and react with more stiffness than others. The rendering is still just 2D canvas. Each cell in the grid is split into triangles, and every triangle is drawn with its own transform so the texture stays locked to the surface while it deforms. Then a shading pass adds highlights and shadows from the fake depth and crease values. No WebGL, no shaders. Just mesh math, texture sampling.
0:21

Paper mesh deformation with pure 2D canvas API. The sheet is built as a grid of points, not as one flat image. Each point keeps its base position, current position, previous position, and a small fake depth value. When I drag one area, the code pulls the nearest point and spreads that force through the grid, so the paper bends instead of just skewing like a card. The structure is held together with constraints between points. Horizontal, vertical, diagonal, and longer links all try to stay close to their original length. That is what gives it paper-like resistance. It can flex, but it does not stretch too far or collapse too much. The solver runs many times per frame, which keeps the shape stable while dragging. The fold detail is driven by texture data. One image is the visible paper surface. Another image is sampled as a fold map: dark values become stronger fold areas, and image gradients give fold direction. That data feeds back into the mesh, so some parts lift more, crease more, and react with more stiffness than others. The rendering is still just 2D canvas. Each cell in the grid is split into triangles, and every triangle is drawn with its own transform so the texture stays locked to the surface while it deforms. Then a shading pass adds highlights and shadows from the fake depth and crease values. No WebGL, no shaders. Just mesh math, texture sampling.

Alex Barashkov

17,732 просмотров • 7 месяцев назад

“But I saved the history on CD, DVD, Magnetics” That data will all decay in a MTBF of +\-50 years. The cloud is deleting as much data that is being produced daily. At some point in the future we would have lost a majority of the 2000s-2040s. We are the amnesia generation.
2:20

“But I saved the history on CD, DVD, Magnetics” That data will all decay in a MTBF of +\-50 years. The cloud is deleting as much data that is being produced daily. At some point in the future we would have lost a majority of the 2000s-2040s. We are the amnesia generation.

Brian Roemmele

410,437 просмотров • 2 лет назад

Geometry of Machine Learning Models - Gaussian Process Kernel In 1948 Norbert Wiener framed prediction as a correlation problem, and in the 1970s George Wahba clarified that picking a smoothness preference is the same as picking a kernel. The motivation is that whenever data i s sparse and noisy, you don't just want a fit, you want a fit with calibrated uncertainty.
0:30

Geometry of Machine Learning Models - Gaussian Process Kernel In 1948 Norbert Wiener framed prediction as a correlation problem, and in the 1970s George Wahba clarified that picking a smoothness preference is the same as picking a kernel. The motivation is that whenever data i s sparse and noisy, you don't just want a fit, you want a fit with calibrated uncertainty.

Mathelirium

15,661 просмотров • 7 месяцев назад

The biggest marketplace on Earth won't be the assets humans own. It'll be the data AI needs. Everything that can be digitised is getting pulled in to train the next models. Every scientific dataset, every piece of research sitting in a university, every sensor reading off every John Deere tractor in a field. All of it feeds the machine, and almost none of it is visible to us. What comes out is an agentic economy running at machine speed. You plug your data into a vault, and agents monetise it on your behalf, trading with other agents in real time, in a marketplace we never see. The company sitting on proprietary data becomes part of it without even knowing. This is what the Economic Singularity actually looks like from the inside. The real economy stops being the one we can see and price, and moves somewhere we can't follow. You own a piece of it, or you get priced out of it. Jordi Visser.
1:27

The biggest marketplace on Earth won't be the assets humans own. It'll be the data AI needs. Everything that can be digitised is getting pulled in to train the next models. Every scientific dataset, every piece of research sitting in a university, every sensor reading off every John Deere tractor in a field. All of it feeds the machine, and almost none of it is visible to us. What comes out is an agentic economy running at machine speed. You plug your data into a vault, and agents monetise it on your behalf, trading with other agents in real time, in a marketplace we never see. The company sitting on proprietary data becomes part of it without even knowing. This is what the Economic Singularity actually looks like from the inside. The real economy stops being the one we can see and price, and moves somewhere we can't follow. You own a piece of it, or you get priced out of it. Jordi Visser.

Raoul Pal

79,211 просмотров • 3 месяцев назад

AI runs on electricity, and Sweden has a head start. This morning at Ruinen we put the question on the table: is the next wave of AI data centres a Swedish opportunity, and what does the grid need to make it happen?
0:37

AI runs on electricity, and Sweden has a head start. This morning at Ruinen we put the question on the table: is the next wave of AI data centres a Swedish opportunity, and what does the grid need to make it happen?

Hitachi Energy

6,945,271 просмотров • 4 месяцев назад

The Torus Becomes the Canvas A Jacobi Theta Function lives naturally on a complex torus. Instead of drawing it on a flat plane, we wrapped the mathematics onto the torus. The surface is driven by θ₁(z|τ), with its moving zeros, phase winding, and logarithmic derivative shaping the colour, seams, and raised divisor points across the geometry. What you are see is a periodic quantum-like field painted onto the space where it actually belongs. #JacobiTheta #ComplexTorus #MathematicalArt #ComplexAnalysis #RiemannSurfaces #MathAnimation
0:33

The Torus Becomes the Canvas A Jacobi Theta Function lives naturally on a complex torus. Instead of drawing it on a flat plane, we wrapped the mathematics onto the torus. The surface is driven by θ₁(z|τ), with its moving zeros, phase winding, and logarithmic derivative shaping the colour, seams, and raised divisor points across the geometry. What you are see is a periodic quantum-like field painted onto the space where it actually belongs. #JacobiTheta #ComplexTorus #MathematicalArt #ComplexAnalysis #RiemannSurfaces #MathAnimation

Mathelirium

22,197 просмотров • 4 месяцев назад

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 просмотров • 3 лет назад

Former Meta Chief AI Scientist Yann LeCun on the three paradigms of machine learning — and why the third is what made ChatGPT possible: Here's each one, and where it breaks. First, supervised learning. You tell the machine the answer. "You show it a picture, let's say of a table, and you tell it this is a table. So it's supervised because you tell it what the correct answer is." Get it wrong, and the machine rewrites itself: "The system computes its output, and if it says something else than table, then it's going to adjust its parameters, its internal structure, so that the output it produces gets closer to the output you want." Repeat at scale and something more than memorisation appears: "Eventually the system will find a way to recognize every image you trained it on, but also images it's never seen that are similar to the one you train it on. This is called a generalization ability." The limit: a human has to supply every single answer. That doesn't scale to the size of the internet. Second, reinforcement learning. You don't give the answer, only a verdict. "You don't tell the system what the correct answer is. You only tell it whether the answer it produced was good or bad." Learning to ride a bike, essentially: "You try to ride a bike and you don't know how to ride the bike and after a while you fall. So you know you did something bad and so you change your strategy a little bit. And eventually you learn how to ride a bike." For years the field assumed this was the closest thing to how animals actually learn. Yann LeCun's verdict: "Now it turns out reinforcement learning is extremely inefficient." It dominates wherever failure is free: "It works really well if you want to train a system to play chess or play go or poker, because you can have the system play millions and millions of games against itself and basically fine-tune itself. But it doesn't really work in the real world." The limit, in one image: "If you want to train a car to drive itself, you're not going to do it with reinforcement learning. It's going to crash thousands of times." On robotics he's careful rather than dismissive: "Reinforcement learning can be part of the solution, but it's not the complete answer. It's not sufficient." Third, self-supervised learning. You tell the machine nothing at all. "And this is what has enabled the recent progress in natural language understanding and chatbots." The strange part is that you stop asking for a task: "You don't train the system to accomplish any particular task. You just train it to basically capture the structure..." The method is deliberate sabotage: "You take a piece of text, you corrupt it in some way, by for example removing some words, and then you train a big neural net to predict the words that are missing." And one narrow version of that trick runs every chatbot on Earth: "A special case of this is that you take a piece of text and the last word in that text is not visible, and so you train the system to predict the last word in that text — and this is the way large language models are trained on." So why did the third one win? Supervised learning needs a human. Reinforcement learning needs a crash. Self-supervised learning needs neither — because the missing word and the correct answer are the same thing. The data grades itself.
2:58

Former Meta Chief AI Scientist Yann LeCun on the three paradigms of machine learning — and why the third is what made ChatGPT possible: Here's each one, and where it breaks. First, supervised learning. You tell the machine the answer. "You show it a picture, let's say of a table, and you tell it this is a table. So it's supervised because you tell it what the correct answer is." Get it wrong, and the machine rewrites itself: "The system computes its output, and if it says something else than table, then it's going to adjust its parameters, its internal structure, so that the output it produces gets closer to the output you want." Repeat at scale and something more than memorisation appears: "Eventually the system will find a way to recognize every image you trained it on, but also images it's never seen that are similar to the one you train it on. This is called a generalization ability." The limit: a human has to supply every single answer. That doesn't scale to the size of the internet. Second, reinforcement learning. You don't give the answer, only a verdict. "You don't tell the system what the correct answer is. You only tell it whether the answer it produced was good or bad." Learning to ride a bike, essentially: "You try to ride a bike and you don't know how to ride the bike and after a while you fall. So you know you did something bad and so you change your strategy a little bit. And eventually you learn how to ride a bike." For years the field assumed this was the closest thing to how animals actually learn. Yann LeCun's verdict: "Now it turns out reinforcement learning is extremely inefficient." It dominates wherever failure is free: "It works really well if you want to train a system to play chess or play go or poker, because you can have the system play millions and millions of games against itself and basically fine-tune itself. But it doesn't really work in the real world." The limit, in one image: "If you want to train a car to drive itself, you're not going to do it with reinforcement learning. It's going to crash thousands of times." On robotics he's careful rather than dismissive: "Reinforcement learning can be part of the solution, but it's not the complete answer. It's not sufficient." Third, self-supervised learning. You tell the machine nothing at all. "And this is what has enabled the recent progress in natural language understanding and chatbots." The strange part is that you stop asking for a task: "You don't train the system to accomplish any particular task. You just train it to basically capture the structure..." The method is deliberate sabotage: "You take a piece of text, you corrupt it in some way, by for example removing some words, and then you train a big neural net to predict the words that are missing." And one narrow version of that trick runs every chatbot on Earth: "A special case of this is that you take a piece of text and the last word in that text is not visible, and so you train the system to predict the last word in that text — and this is the way large language models are trained on." So why did the third one win? Supervised learning needs a human. Reinforcement learning needs a crash. Self-supervised learning needs neither — because the missing word and the correct answer are the same thing. The data grades itself.

Big Brain AI

49,293 просмотров • 2 месяцев назад

IN 1986 MIT FILMED THE LECTURE WHERE CODE STOPPED BEING CODE AND BECAME DATA 43 minutes from Gerald Sussman, in the most legendary intro programming course ever recorded. -> The idea that lands: to a program, your code is just data it can read and rewrite. He builds a program that does real calculus -- not by crunching numbers, but by reading the math as a list and transforming it piece by piece. Then he shows the trick hiding under all of it: in this language, code and data are the same material. Forty years later that is exactly what an AI coding agent is -- a program that reads your code as data, rewrites it, and hands it back. Sussman drew the whole idea on a blackboard in 1986. Writing code was never the deepest skill -- understanding that code itself is data a program can manipulate is. This is where you learn it. Most people think AI writing code is brand new. The ones who watch this saw the blueprint 40 years ago. Bookmark & Watch it. This one's a legend ↓
43:30

IN 1986 MIT FILMED THE LECTURE WHERE CODE STOPPED BEING CODE AND BECAME DATA 43 minutes from Gerald Sussman, in the most legendary intro programming course ever recorded. -> The idea that lands: to a program, your code is just data it can read and rewrite. He builds a program that does real calculus -- not by crunching numbers, but by reading the math as a list and transforming it piece by piece. Then he shows the trick hiding under all of it: in this language, code and data are the same material. Forty years later that is exactly what an AI coding agent is -- a program that reads your code as data, rewrites it, and hands it back. Sussman drew the whole idea on a blackboard in 1986. Writing code was never the deepest skill -- understanding that code itself is data a program can manipulate is. This is where you learn it. Most people think AI writing code is brand new. The ones who watch this saw the blueprint 40 years ago. Bookmark & Watch it. This one's a legend ↓

slash1s

22,107 просмотров • 4 месяцев назад

The Archimedean spiral is one of the oldest curves in mathematics, with turns that stay evenly spaced. Here, a straight line slowly turns into this spiral, and four hundred connected points follow its shape.
0:23

The Archimedean spiral is one of the oldest curves in mathematics, with turns that stay evenly spaced. Here, a straight line slowly turns into this spiral, and four hundred connected points follow its shape.

The Math Flow

23,417 просмотров • 19 дней назад

There's a fruit fly walking around right now that was never born. eon just released a video where they took a real fly's connectome — the wiring diagram of its brain — and simulated it. Dropped it into a virtual body. It started walking. Grooming. Feeding. Doing what flies do. Nobody taught it to walk. No training data, no gradient descent toward fly-like behavior. This is the opposite of how AI works. They rebuilt the mind from the inside, neuron by neuron, and behavior just... emerged. It's the first time a biological organism has been recreated not by modeling what it does, but by modeling what it is. A human brain is 6 OOM more neurons. That's a scaling problem, something we've gotten very good at solving. So what happens when we have a working copy of the human mind?
0:34

There's a fruit fly walking around right now that was never born. eon just released a video where they took a real fly's connectome — the wiring diagram of its brain — and simulated it. Dropped it into a virtual body. It started walking. Grooming. Feeding. Doing what flies do. Nobody taught it to walk. No training data, no gradient descent toward fly-like behavior. This is the opposite of how AI works. They rebuilt the mind from the inside, neuron by neuron, and behavior just... emerged. It's the first time a biological organism has been recreated not by modeling what it does, but by modeling what it is. A human brain is 6 OOM more neurons. That's a scaling problem, something we've gotten very good at solving. So what happens when we have a working copy of the human mind?

hattie

9,598,981 просмотров • 7 месяцев назад

New PNAS paper. Historical GDP per capita data is scarce, but data on the places of birth, death, and occupations of famous individuals is abundant. In this paper we estimate the historical GDP per capita of hundreds of regions in Europe and North America using a machine learning model that leveraged data on about 500k famous biographies. Our estimates more-or-less quadruple the availability of historical GDP per capita estimates for the last 700 years. So why use biographies to augment historical GDP per capita data? Biographical data contains information about people who might have contributed directly to economic growth, like James Watt, or that were attracted to wealthy places looking for patrons, like Michelangelo. So we--mainly Philipp (Philipp Koch)--used this data to construct hundreds of features describing each European region. Then, we trained a machine learning model to find the features that explained most of the variance in a cross-validation test, where we split regions multiple times into a training set and a test set. On average, the model explained about 90% of the variance in GDP per capita of the regions it had not seen during training. But we wanted to go further, and Philipp really went to town by looking at different ways to validate our estimates. We found our estimates correlate positively with historical measures of wellbeing, church building activity, urbanization, and body height. We also used these measures to reproduce the basic Atlantic trade result of Acemoglu, Johnson, and Robison and to explore the economic consequences of the famous Lisbon earthquake of 1755. But what I personally loved most about this project, other than working with Philipp Koch and V, is that it shows that we can use machine learning methods not only to explore the future, but the past. There is a bright and growing future in the use of machine learning for economic history. Hope you enjoy the paper and the data. You can find links to the paper and a data exploration tool in the first comment.
3:25

New PNAS paper. Historical GDP per capita data is scarce, but data on the places of birth, death, and occupations of famous individuals is abundant. In this paper we estimate the historical GDP per capita of hundreds of regions in Europe and North America using a machine learning model that leveraged data on about 500k famous biographies. Our estimates more-or-less quadruple the availability of historical GDP per capita estimates for the last 700 years. So why use biographies to augment historical GDP per capita data? Biographical data contains information about people who might have contributed directly to economic growth, like James Watt, or that were attracted to wealthy places looking for patrons, like Michelangelo. So we--mainly Philipp (Philipp Koch)--used this data to construct hundreds of features describing each European region. Then, we trained a machine learning model to find the features that explained most of the variance in a cross-validation test, where we split regions multiple times into a training set and a test set. On average, the model explained about 90% of the variance in GDP per capita of the regions it had not seen during training. But we wanted to go further, and Philipp really went to town by looking at different ways to validate our estimates. We found our estimates correlate positively with historical measures of wellbeing, church building activity, urbanization, and body height. We also used these measures to reproduce the basic Atlantic trade result of Acemoglu, Johnson, and Robison and to explore the economic consequences of the famous Lisbon earthquake of 1755. But what I personally loved most about this project, other than working with Philipp Koch and V, is that it shows that we can use machine learning methods not only to explore the future, but the past. There is a bright and growing future in the use of machine learning for economic history. Hope you enjoy the paper and the data. You can find links to the paper and a data exploration tool in the first comment.

César A. Hidalgo

54,365 просмотров • 2 лет назад

I don’t know if we live in a Matrix, but I know for sure that robots will spend most of their lives in simulation. Let machines train machines. I’m excited to introduce DexMimicGen, a massive-scale synthetic data generator that enables a humanoid robot to learn complex skills from only a handful of human demonstrations. Yes, as few as 5! DexMimicGen addresses the biggest pain point in robotics: where do we get data? Unlike with LLMs, where vast amounts of texts are readily available, you cannot simply download motor control signals from the internet. So researchers teleoperate the robots to collect motion data via XR headsets. They have to repeat the same skill over and over and over again, because neural nets are data hungry. This is a very slow and uncomfortable process. At NVIDIA, we believe the majority of high-quality tokens for robot foundation models will come from simulation. What DexMimicGen does is to trade GPU compute time for human time. It takes one motion trajectory from human, and multiplies into 1000s of new trajectories. A robot brain trained on this augmented dataset will generalize far better in the real world. Think of DexMimicGen as a learning signal amplifier. It maps a small dataset to a large (de facto infinite) dataset, using physics simulation in the loop. In this way, we free humans from babysitting the bots all day. The future of robot data is generative. The future of the entire robot learning pipeline will also be generative. 🧵
0:58

I don’t know if we live in a Matrix, but I know for sure that robots will spend most of their lives in simulation. Let machines train machines. I’m excited to introduce DexMimicGen, a massive-scale synthetic data generator that enables a humanoid robot to learn complex skills from only a handful of human demonstrations. Yes, as few as 5! DexMimicGen addresses the biggest pain point in robotics: where do we get data? Unlike with LLMs, where vast amounts of texts are readily available, you cannot simply download motor control signals from the internet. So researchers teleoperate the robots to collect motion data via XR headsets. They have to repeat the same skill over and over and over again, because neural nets are data hungry. This is a very slow and uncomfortable process. At NVIDIA, we believe the majority of high-quality tokens for robot foundation models will come from simulation. What DexMimicGen does is to trade GPU compute time for human time. It takes one motion trajectory from human, and multiplies into 1000s of new trajectories. A robot brain trained on this augmented dataset will generalize far better in the real world. Think of DexMimicGen as a learning signal amplifier. It maps a small dataset to a large (de facto infinite) dataset, using physics simulation in the loop. In this way, we free humans from babysitting the bots all day. The future of robot data is generative. The future of the entire robot learning pipeline will also be generative. 🧵

Jim Fan

165,488 просмотров • 2 лет назад