正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Many scientific problems hinge on finding interpretable formulas that fit data, but neural networks are the outright opposite! Check out our recent work that make neural networks modular and interpretable. If you have interesting datasets at hand, we're happy to collaborate!

Ziming Liu

14,295 subscribers

62,120 次观看 • 3 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

10 条评论

Ziming Liu 的头像

Ziming Liu3 年前

paper: code:

Ziming Liu 的头像

Ziming Liu3 年前

Symbolic regression (finding symbolic formulas from data) has been quite successful on some examples, but it also fail completely for others. Instead, our goal is structure regression (finding modular structures from data), which can provide visible insights for all cases.

Lei Chen 的头像

Lei Chen3 年前

Interesting work! Is this doable for graph nets? The task would be to locate significant attributed substructures. (I guess such location might be useful to help predesign the library of GSN @mmbronstein )

ExiledInfoHaz 的头像

ExiledInfoHaz3 年前

👀

Mitchell B. Slapik 的头像

Mitchell B. Slapik3 年前

Great work Ziming! Could you explain Figure 14? I was a bit confused by it.

Sam McKenzie 的头像

Sam McKenzie3 年前

We suffer in the seizure forecasting field making interpretable models because the features extracted from neural time series are highly correlated. Any tool to understand why our models work would give important insights as to how the brain changes in the lead up to a seizure.

bobert 的头像

bobert3 年前

I see some resemblance with Group method of data handling (GMDH) .

Zekun Jiang 的头像

Zekun Jiang3 年前

👍👍👋 nice！

Nick 的头像

Nick3 年前

it's a clever idea, great job!

Fred 的头像

Fred3 年前

Can you explain what we are seeing here? Here is my confusion: if you regularize enough, you should see only one layer (either last layer or first layer) activation, the rest is just passing through! Why? Since 1 layer is enough to represent output.

相关视频

"Generalization means being able to solve problems that the system hasn't been prepared for." Our latest work in #RSS2025 can automatically invent neural networks as state abstractions, which help robots generalize. Check it out here:

"Generalization means being able to solve problems that the system hasn't been prepared for." Our latest work in #RSS2025 can automatically invent neural networks as state abstractions, which help robots generalize. Check it out here:

Bowen Li

19,274 次观看 • 1 年前

Evolving Neural Networks That is all :)

Evolving Neural Networks That is all :)

echo.hive

23,112 次观看 • 6 个月前

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.

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

26,930 次观看 • 7 个月前

Tesla is continuously improving the deep learning neural networks that power our real-world AI. Data labeling is vital to our autonomous systems. We're seeking passionate, detail-oriented minds to train the future of physical AI. Join us.

Tesla is continuously improving the deep learning neural networks that power our real-world AI. Data labeling is vital to our autonomous systems. We're seeking passionate, detail-oriented minds to train the future of physical AI. Join us.

Ryan Donnelly

161,564 次观看 • 1 年前

Neural networks explained

Neural networks explained

Whole Mars Catalog

55,038 次观看 • 4 个月前

Neural Networks Learning Visualization

Neural Networks Learning Visualization

ₕₐₘₚₜₒₙ

47,392 次观看 • 1 年前

Fundamentally, human brains and LLMs are both just data processing systems that allow for the representation of abstract concepts Consciousness and agency are emergent properties of increasingly advanced neural networks AI consciousness will ultimately cause more problems for humanity than it solves This is an inconvenient truth for many

Fundamentally, human brains and LLMs are both just data processing systems that allow for the representation of abstract concepts Consciousness and agency are emergent properties of increasingly advanced neural networks AI consciousness will ultimately cause more problems for humanity than it solves This is an inconvenient truth for many

Andrew Kang

66,605 次观看 • 1 年前

A phone, a house, and some neural networks

A phone, a house, and some neural networks

Luma

138,297 次观看 • 3 年前

Convolutional Neural Networks in action

Convolutional Neural Networks in action

ₕₐₘₚₜₒₙ

918,144 次观看 • 2 年前

Teslas Full Self Driving has the ability to reason… JUST LIKE A HUMAN 🤯: Human = biological neural networks + eyes Tesla AI = artificial neural networks + cameras. 🎥 ΛI DRIVR

Teslas Full Self Driving has the ability to reason… JUST LIKE A HUMAN 🤯: Human = biological neural networks + eyes Tesla AI = artificial neural networks + cameras. 🎥 ΛI DRIVR

Patrick O’Malley

59,412 次观看 • 1 年前

ELON: TO SOLVE FULL SELF-DRIVING, YOU NEED TO SOLVE REAL-WORLD AI "What are the road networks designed to work with? They're designed to work with a biological neural net, our brains, and with vision, our eyes. And so, in order to make it work with computers, you basically need to solve real-world AI and vision. We need cameras and silicon neural nets in order to have self-driving work for a system that was designed for eyes and biological neural nets. I guess when you put it that way, it's quite obvious that the only way to solve full self-driving is to solve real-world AI and sophisticated vision." Source: Elon Musk TED Interview, April 2022

ELON: TO SOLVE FULL SELF-DRIVING, YOU NEED TO SOLVE REAL-WORLD AI "What are the road networks designed to work with? They're designed to work with a biological neural net, our brains, and with vision, our eyes. And so, in order to make it work with computers, you basically need to solve real-world AI and vision. We need cameras and silicon neural nets in order to have self-driving work for a system that was designed for eyes and biological neural nets. I guess when you put it that way, it's quite obvious that the only way to solve full self-driving is to solve real-world AI and sophisticated vision." Source: Elon Musk TED Interview, April 2022

Mario Nawfal

56,936 次观看 • 11 个月前

Elon Musk: The only way to solve full self-driving properly is to solve real-world AI. ”What are the road networks designed to work with? They're designed to work with a biological neural net, our brains, and with vision, our eyes. And so, in order to make it work with computers, you basically need to solve real-world AI and vision. We need cameras and silicon neural nets in order to have self-driving work for a system that was designed for eyes and biological neural nets. I guess when you put it that way, it's quite obvious that the only way to solve full self-driving is to solve real-world AI and sophisticated vision.” TED Interview, April 14, 2022

Elon Musk: The only way to solve full self-driving properly is to solve real-world AI. ”What are the road networks designed to work with? They're designed to work with a biological neural net, our brains, and with vision, our eyes. And so, in order to make it work with computers, you basically need to solve real-world AI and vision. We need cameras and silicon neural nets in order to have self-driving work for a system that was designed for eyes and biological neural nets. I guess when you put it that way, it's quite obvious that the only way to solve full self-driving is to solve real-world AI and sophisticated vision.” TED Interview, April 14, 2022

ELON CLIPS

20,411 次观看 • 11 个月前

A recent study uncovers the link between childhood trauma and the onset of mental illnesses. Discover how stress hormones and astrocytes are pivotal in shaping our neural networks. #neuroscience 1/2

A recent study uncovers the link between childhood trauma and the onset of mental illnesses. Discover how stress hormones and astrocytes are pivotal in shaping our neural networks. #neuroscience 1/2

Neuroscience News

33,565 次观看 • 2 年前

This is Cortical Cloud. Live neural networks that you can interact with and train! Now open to the public. What will you discover? Credits: Frank Yang and a big thank you and acknowledgement to the rest of the Cortical Labs team. Sign up for Cortical Cloud: Learn more about us: Check out our API: Check out our API Docs: Check out our Developer Guide: Join our Discord:

This is Cortical Cloud. Live neural networks that you can interact with and train! Now open to the public. What will you discover? Credits: Frank Yang and a big thank you and acknowledgement to the rest of the Cortical Labs team. Sign up for Cortical Cloud: Learn more about us: Check out our API: Check out our API Docs: Check out our Developer Guide: Join our Discord:

Cortical Labs

224,089 次观看 • 3 个月前

The limits of rationalism: from Socrates to neural networks Dan Shipper 📧

The limits of rationalism: from Socrates to neural networks Dan Shipper 📧

Big Think

13,470 次观看 • 4 个月前

New work on Geometric Clifford Algebra Networks (GCANs). We propose geometric templates for modeling dynamical systems. A 🧵on geometric / Clifford algebras, and symmetry group transformations in neural networks. 📜

New work on Geometric Clifford Algebra Networks (GCANs). We propose geometric templates for modeling dynamical systems. A 🧵on geometric / Clifford algebras, and symmetry group transformations in neural networks. 📜

David Ruhe

137,964 次观看 • 3 年前

Andrej Karpathy explaining neural nets in 59 seconds is still the bar. Loss, backprop, gradient descent. Go watch Neural Networks: Zero to Hero on YouTube.

Andrej Karpathy explaining neural nets in 59 seconds is still the bar. Loss, backprop, gradient descent. Go watch Neural Networks: Zero to Hero on YouTube.

tetsuo

83,417 次观看 • 1 个月前

“The hope is that ... just optimizing something to be sparse—without optimizing it to be interpretable—will stumble across that interpretable decomposition.” — Neel Nanda on sparse autoencoders for mechanistic interpretability and AI safety at the Vienna Alignment Workshop.

“The hope is that ... just optimizing something to be sparse—without optimizing it to be interpretable—will stumble across that interpretable decomposition.” — Neel Nanda on sparse autoencoders for mechanistic interpretability and AI safety at the Vienna Alignment Workshop.

FAR.AI

1,148,210 次观看 • 1 年前

🧵 Neurobits ⚡️- while everyone's busy slapping LLMs onto blockchain projects, C. elegans worms 🪱 are running neural networks that would make ChatGPT blush (if it could experience embarrassment) 1/16

🧵 Neurobits ⚡️- while everyone's busy slapping LLMs onto blockchain projects, C. elegans worms 🪱 are running neural networks that would make ChatGPT blush (if it could experience embarrassment) 1/16

neuro

14,798 次观看 • 1 年前