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。

New article! A visual, interactive intro to Neural Networks, backprop, and more! I hope the easiest resource to learn Neural Networks! #Datavisualization #dataviz #RStats #DataScience #scicomm #svelte #d3js #MachineLearning #ai

Jared Wilber

3,572 subscribers

18,137 次观看 • 3 年前 •via X (Twitter)

科学技术 #Datavisualization #dataviz #RStats #DataScience #scicomm #svelte #d3js #MachineLearning #ai

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

1/ Microsoft - Artificial Intelligence for Beginners: This 24 lesson curriculum includes following topics: - Symbolic AI - Neural Networks - Computer Vision - NLP - and more The curriculum includes hands-on lessons, quizzes, and labs. Learn more:

1/ Microsoft - Artificial Intelligence for Beginners: This 24 lesson curriculum includes following topics: - Symbolic AI - Neural Networks - Computer Vision - NLP - and more The curriculum includes hands-on lessons, quizzes, and labs. Learn more:

Shruti

15,828 次观看 • 2 年前

Day 12 of learning AI bs from scratch > a look into recurrent neural networks (RNN's) > learned about Long Short-Term Memory > read couple chapters of > drawbacks of RNN's > Simple Neural networks → CNN → RNN will try and train one MLP, CNN and a RNN from scratch next and try and summarize its working it a blog. back to doing based learning after this, much more retention like that.

Day 12 of learning AI bs from scratch > a look into recurrent neural networks (RNN's) > learned about Long Short-Term Memory > read couple chapters of > drawbacks of RNN's > Simple Neural networks → CNN → RNN will try and train one MLP, CNN and a RNN from scratch next and try and summarize its working it a blog. back to doing based learning after this, much more retention like that.

Arham Amin

62,415 次观看 • 1 个月前

General relativity 🤝 neural fields This simulation of a black hole is coming from our neural networks 🚀 We introduce Einstein Fields, a compact NN representation for 4D numerical relativity. EinFields are designed to handle the tensorial properties of GR and its derivatives.

General relativity 🤝 neural fields This simulation of a black hole is coming from our neural networks 🚀 We introduce Einstein Fields, a compact NN representation for 4D numerical relativity. EinFields are designed to handle the tensorial properties of GR and its derivatives.

Johannes Brandstetter

39,516 次观看 • 1 年前

Robot paper of the day: RoboBallet: Planning for multirobot reaching with graph neural networks and reinforcement learning UCL + Google DeepMind + Intrinsic built an AI planner that choreographs teams of arms to work in tight spaces without collisions—planning in seconds, not days.

Robot paper of the day: RoboBallet: Planning for multirobot reaching with graph neural networks and reinforcement learning UCL + Google DeepMind + Intrinsic built an AI planner that choreographs teams of arms to work in tight spaces without collisions—planning in seconds, not days.

Jiafei Duan

15,084 次观看 • 1 年前

🇨🇳 Chinese CS servers hitting different lately The game is straight-up flooded with bots running full neural networks 🙂 They don’t just ruin team balance, they’re also talking to each other in voice chat and shilling their AI in text… Marketers, take notes 🤡

🇨🇳 Chinese CS servers hitting different lately The game is straight-up flooded with bots running full neural networks 🙂 They don’t just ruin team balance, they’re also talking to each other in voice chat and shilling their AI in text… Marketers, take notes 🤡

Steam Inventory Helper

132,816 次观看 • 5 个月前

Bringing new meaning to the word NeRD at #CoRL2025. 🤓 Neural Robot Dynamics (NeRD) bridges the sim-to-real gap with a hybrid of neural modeling and analytical simulation, unlocking zero-shot transfer and continuous learning loops for optimal robotics training. Read more & try it in Newton 🤖

Bringing new meaning to the word NeRD at #CoRL2025. 🤓 Neural Robot Dynamics (NeRD) bridges the sim-to-real gap with a hybrid of neural modeling and analytical simulation, unlocking zero-shot transfer and continuous learning loops for optimal robotics training. Read more & try it in Newton 🤖

NVIDIA Robotics

17,556 次观看 • 11 个月前

🏠 How can AI understand the structure of an entire building from images? PolyLayout introduces a new approach for multi-room 3D layout estimation — allowing AI to jointly reconstruct connected indoor spaces instead of treating every room independently. By combining neural networks with explicit geometric reasoning, PolyLayout predicts more accurate and robust room layouts while adapting to different scenes and camera setups. A step closer to machines that can truly understand the spaces around us. 🧠🏗️ Paper Title: PolyLayout: Multi-room Manhattan Layout Estimation Project: Link:

🏠 How can AI understand the structure of an entire building from images? PolyLayout introduces a new approach for multi-room 3D layout estimation — allowing AI to jointly reconstruct connected indoor spaces instead of treating every room independently. By combining neural networks with explicit geometric reasoning, PolyLayout predicts more accurate and robust room layouts while adapting to different scenes and camera setups. A step closer to machines that can truly understand the spaces around us. 🧠🏗️ Paper Title: PolyLayout: Multi-room Manhattan Layout Estimation Project: Link:

AI Bites | YouTube Channel

33,047 次观看 • 1 个月前

Hi all, I just posted a new visual article in my blog, made with threejs: I like to learn new things, and use this blog to document my learnings. This one started when I got curious about spherical helix and want to learn about it, and ended up learning about parametric equations

Hi all, I just posted a new visual article in my blog, made with threejs: I like to learn new things, and use this blog to document my learnings. This one started when I got curious about spherical helix and want to learn about it, and ended up learning about parametric equations

Damar

18,889 次观看 • 1 年前

It's been incredible to see neural networks working so well on our humanoid robots Humanoids are crazy complex - an individual motor can rotate 360 degrees and you have 40+ joints. If you do the math, that means more possible robot states than atoms in the universe Figure has our own AI model called Helix that we've designed in-house. A single Helix neural network now outputs both manipulation and navigation, end-to-end from language and pixel input Every leap in machine learning has come from massive, diverse datasets. At Figure, we’re currently building the largest pretraining dataset for humanoids in history - excited to see what this unlocks

It's been incredible to see neural networks working so well on our humanoid robots Humanoids are crazy complex - an individual motor can rotate 360 degrees and you have 40+ joints. If you do the math, that means more possible robot states than atoms in the universe Figure has our own AI model called Helix that we've designed in-house. A single Helix neural network now outputs both manipulation and navigation, end-to-end from language and pixel input Every leap in machine learning has come from massive, diverse datasets. At Figure, we’re currently building the largest pretraining dataset for humanoids in history - excited to see what this unlocks

Brett Adcock

93,986 次观看 • 11 个月前

$🚨🇷🇺🇨🇳 Russia and China develop breakthrough AI-powered earthquake forecasting method The new AI model predicts earthquakes by tracking changes in the Earth’s crust with superior accuracy—at a fraction of traditional computing costs. 🔸 Geoacoustic emissions are used — sounds produced as tectonic stress builds up underground — to pinpoint possible earthquake precursors 🔸The new system combines Physics-Informed Neural Networks (PINNs) with Kolmogorov-Arnold Networks (KANs) to process seismic data 🔸 The team proposes using human-made noise as seismic sonar to reveal underground details that natural signals miss 🔸 The approach slashes computing costs while delivering sharper 2D and 3D geological maps Beyond earthquake forecasting, the same technology could also aid mineral exploration and infrastructure planning—by revealing subsurface structures with unprecedented clarity$

🚨🇷🇺🇨🇳 Russia and China develop breakthrough AI-powered earthquake forecasting method The new AI model predicts earthquakes by tracking changes in the Earth’s crust with superior accuracy—at a fraction of traditional computing costs. 🔸 Geoacoustic emissions are used — sounds produced as tectonic stress builds up underground — to pinpoint possible earthquake precursors 🔸The new system combines Physics-Informed Neural Networks (PINNs) with Kolmogorov-Arnold Networks (KANs) to process seismic data 🔸 The team proposes using human-made noise as seismic sonar to reveal underground details that natural signals miss 🔸 The approach slashes computing costs while delivering sharper 2D and 3D geological maps Beyond earthquake forecasting, the same technology could also aid mineral exploration and infrastructure planning—by revealing subsurface structures with unprecedented clarity

Sputnik

13,762 次观看 • 2 个月前

🌊 Bluwhale expands its multi-chain intelligence layer with Solana support. Bluwhale now supports Solana Network, allowing users to connect their Solana wallets and explore the Bluwhale ecosystem across more networks. By expanding multi-chain accessibility, Bluwhale continues building a more connected foundation for Web3’s Intelligence Layer and AI-native finance. More networks. More intelligence. More possibilities. 🐳

🌊 Bluwhale expands its multi-chain intelligence layer with Solana support. Bluwhale now supports Solana Network, allowing users to connect their Solana wallets and explore the Bluwhale ecosystem across more networks. By expanding multi-chain accessibility, Bluwhale continues building a more connected foundation for Web3’s Intelligence Layer and AI-native finance. More networks. More intelligence. More possibilities. 🐳

Bluwhale

24,081 次观看 • 1 个月前

“When you connect nodes together, you're designing a workflow that moves and thinks like you do.” Learn the basics in our Intro to Fuser: A Visual Workspace for AI-Powered Creative Workflows. 🔗 ↓

“When you connect nodes together, you're designing a workflow that moves and thinks like you do.” Learn the basics in our Intro to Fuser: A Visual Workspace for AI-Powered Creative Workflows. 🔗 ↓

Fuser

21,284 次观看 • 9 个月前

🌏ICE HSI Attaché Ernest Verina and his team in Australia work closely with the Australian Federal Police, New Zealand Police, and partner agencies across the Pacific to disrupt transnational criminal networks profiting off illegal narcotics trafficking, child exploitation and other global crimes. ➡️Learn more:

🌏ICE HSI Attaché Ernest Verina and his team in Australia work closely with the Australian Federal Police, New Zealand Police, and partner agencies across the Pacific to disrupt transnational criminal networks profiting off illegal narcotics trafficking, child exploitation and other global crimes. ➡️Learn more:

U.S. Immigration and Customs Enforcement

23,617 次观看 • 2 个月前

Today, we're proud to announce that Syndicate Network is one of the FIRST decentralized networks to be built and launched in AMERICA—formed under a Wyoming-based DUNA with no offshore entities. This is a major step forward for the crypto industry and U.S. 🇺🇸 Learn more ↓

Today, we're proud to announce that Syndicate Network is one of the FIRST decentralized networks to be built and launched in AMERICA—formed under a Wyoming-based DUNA with no offshore entities. This is a major step forward for the crypto industry and U.S. 🇺🇸 Learn more ↓

Syndicate

179,222 次观看 • 1 年前

This is a NeRF (Neural Radiance Field) and it's one of the coolest pieces of AI tech out there. To generate this scene, I shot a video on my iPhone, then uploaded to Luma Luma turned it into a NeRF, and then I directed the camera in their editor to create this shot. Don't sleep on NeRFs.

This is a NeRF (Neural Radiance Field) and it's one of the coolest pieces of AI tech out there. To generate this scene, I shot a video on my iPhone, then uploaded to Luma Luma turned it into a NeRF, and then I directed the camera in their editor to create this shot. Don't sleep on NeRFs.

Nick St. Pierre

1,026,518 次观看 • 3 年前

📢 NEW ADOPTION ALERT 📢 We're excited to welcome GriffinAI | The #1 AI Agent Builder for DeFi 🤖 to the Vanar AI agent Ecosystem! 🎉 Griffin AI, a pioneer in decentralized networks for building and monetizing AI agents in Web3, will officially support the Vanar blockchain. Together, we’re driving the next wave of AI innovation.

📢 NEW ADOPTION ALERT 📢 We're excited to welcome GriffinAI | The #1 AI Agent Builder for DeFi 🤖 to the Vanar AI agent Ecosystem! 🎉 Griffin AI, a pioneer in decentralized networks for building and monetizing AI agents in Web3, will officially support the Vanar blockchain. Together, we’re driving the next wave of AI innovation.

Vanar

34,050 次观看 • 1 年前