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。

Introducing Neural Developmental Programs (NDPs)🧬🧠Instead of neural networks with fixed architectures, we allow neural networks to grow through a dynamic self-organizing process, inspired by how biological nervous systems develop👇 PDF:

Sebastian Risi

10,134 subscribers

239,469 次观看 • 2 年前 •via X (Twitter)

科学技术教育

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

⚡Physics-Informed Neural Networks (PINN)⚡ PINNs are neural networks that are trained to solve supervised learning tasks while respecting any given laws of physics described by general nonlinear partial differential equations. 👉 Full Tutorial:

⚡Physics-Informed Neural Networks (PINN)⚡ PINNs are neural networks that are trained to solve supervised learning tasks while respecting any given laws of physics described by general nonlinear partial differential equations. 👉 Full Tutorial:

Jousef Murad

292,120 次观看 • 2 年前

Déda et al. use neural networks for flow analysis & control in nonlinear fluid systems, showcasing accuracy & stabilization in complex dynamics. From the Lorenz system to confined cylinder flows, neural networks shine as effective models & controllers.

Déda et al. use neural networks for flow analysis & control in nonlinear fluid systems, showcasing accuracy & stabilization in complex dynamics. From the Lorenz system to confined cylinder flows, neural networks shine as effective models & controllers.

Physical Review Fluids

11,604 次观看 • 2 年前

Another video from a neural network has gone viral on social networks 😄

Another video from a neural network has gone viral on social networks 😄

Sprinter Observer

48,449 次观看 • 1 年前

Visualization of what is inside of AI models. This represents the layers of interconnected neural networks. And yes patterns do develop and they can form a signature of how they think. The pattern can be seen as the thought process.

Visualization of what is inside of AI models. This represents the layers of interconnected neural networks. And yes patterns do develop and they can form a signature of how they think. The pattern can be seen as the thought process.

Brian Roemmele

1,195,384 次观看 • 6 个月前

New paper: We present a "Unified Neural Scaling Law" functional form that accurately models & extrapolates the multivariate scaling behaviors of artificial neural networks as the variables listed in this attached video are varied. (1/N)

New paper: We present a "Unified Neural Scaling Law" functional form that accurately models & extrapolates the multivariate scaling behaviors of artificial neural networks as the variables listed in this attached video are varied. (1/N)

Ethan Caballero

46,759 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

39,368 次观看 • 11 个月前

Impressive work from Jianping Fu University of Michigan Orly Reiner's Lab Song and Ming Labs describing a new method to grow a bona fide neural tube from human stem cells. NT-like structures develop antero posterior & dorso-ventral polarities as in a normal neural tube, including hox gene segmentation & Neural crest cells. Great tool to study neuronal specification

Impressive work from Jianping Fu University of Michigan Orly Reiner's Lab Song and Ming Labs describing a new method to grow a bona fide neural tube from human stem cells. NT-like structures develop antero posterior & dorso-ventral polarities as in a normal neural tube, including hox gene segmentation & Neural crest cells. Great tool to study neuronal specification

Alain Chédotal

14,458 次观看 • 2 年前

What’s this neural process?

What’s this neural process?

Oren Gottfried, MD

65,831 次观看 • 1 年前

2 robots with individual neural networks putting away unseen groceries (zero shot) Our AI progress is accelerating Figure's timeline for home robots

2 robots with individual neural networks putting away unseen groceries (zero shot) Our AI progress is accelerating Figure's timeline for home robots

Brett Adcock

164,726 次观看 • 1 年前

Imagine: Parallel Neural Networks with Shaders 🤔 (GLSL instead of CUDA) Parallelization by encoding the weights and activations as Buffer Objects or Textures, using fs to perform matmul and activation functions in parallel. Each fragm shader instance parproc 1..n neuron.

Imagine: Parallel Neural Networks with Shaders 🤔 (GLSL instead of CUDA) Parallelization by encoding the weights and activations as Buffer Objects or Textures, using fs to perform matmul and activation functions in parallel. Each fragm shader instance parproc 1..n neuron.

wavefnx

86,634 次观看 • 1 年前

This project argues that latent space—the learned, multidimensional, representational substrate of neural networks—is not only a mathematical construct but, read through literature, a structure akin to architectural interiority that renders the abstract physically legible.

This project argues that latent space—the learned, multidimensional, representational substrate of neural networks—is not only a mathematical construct but, read through literature, a structure akin to architectural interiority that renders the abstract physically legible.

Gašper Beguš

10,671 次观看 • 3 个月前

📢📢📢 NoKSR: Kernel-Free Neural Surface Reconstruction via Point Cloud Serialization #3DV2025 TL;DR: neural reconstruction with a simpler architecture (no linear systems to solve), and up to 3x speedup vs. voxel-based methods!

📢📢📢 NoKSR: Kernel-Free Neural Surface Reconstruction via Point Cloud Serialization #3DV2025 TL;DR: neural reconstruction with a simpler architecture (no linear systems to solve), and up to 3x speedup vs. voxel-based methods!

Andrea Tagliasacchi @CVPR

16,962 次观看 • 1 年前

1. Machine Learning Specialization. Break Into AI with this 3-course program by Andrew Ng. What You’ll learn: → Build ML models → Train neural networks → Deep reinforcement learning → Unsupervised learning techniques 🔗

1. Machine Learning Specialization. Break Into AI with this 3-course program by Andrew Ng. What You’ll learn: → Build ML models → Train neural networks → Deep reinforcement learning → Unsupervised learning techniques 🔗

Abhishek

364,326 次观看 • 1 年前

1. Machine Learning Specialization Break into AI with this 3-course program by Andrew Ng. What you’ll learn: → Build machine learning models → Train neural networks → Deep reinforcement learning → Unsupervised learning techniques 🔗

1. Machine Learning Specialization Break into AI with this 3-course program by Andrew Ng. What you’ll learn: → Build machine learning models → Train neural networks → Deep reinforcement learning → Unsupervised learning techniques 🔗

Amit

55,462 次观看 • 6 个月前

#SIGGRAPHAsia2024 🔥 Replace your Marching Cubes code with our Occupancy-Based Dual Contouring to reveal the "real" shape from either a signed distance function or an occupancy function. No neural networks involved. Web:

#SIGGRAPHAsia2024 🔥 Replace your Marching Cubes code with our Occupancy-Based Dual Contouring to reveal the "real" shape from either a signed distance function or an occupancy function. No neural networks involved. Web:

Minhyuk Sung

14,637 次观看 • 1 年前

How ReLU neural network learns functions?

How ReLU neural network learns functions?

S.T.E.M Explorer

246,104 次观看 • 3 个月前

🚀 Excited to share our #ICLR2025 work on planning with neural dynamics models! While our lab has developed diverse neural dynamics models for manipulating rigid, deformable, and granular objects, having the model alone doesn’t solve the problem—planning with it remains a challenge. 💡 Enter BaB-ND, led by Keyi and Jiangwei! We propose a scalable, GPU-accelerated branch-and-bound algorithm, inspired by neural network verification, to enable effective planning for diverse objects modeled with neural dynamics. 🔗 Project page (open-source + detailed docs!): 🎥 Watch the video to see T being pushed around obstacles, and check out Keyi’s thread for more details!

🚀 Excited to share our #ICLR2025 work on planning with neural dynamics models! While our lab has developed diverse neural dynamics models for manipulating rigid, deformable, and granular objects, having the model alone doesn’t solve the problem—planning with it remains a challenge. 💡 Enter BaB-ND, led by Keyi and Jiangwei! We propose a scalable, GPU-accelerated branch-and-bound algorithm, inspired by neural network verification, to enable effective planning for diverse objects modeled with neural dynamics. 🔗 Project page (open-source + detailed docs!): 🎥 Watch the video to see T being pushed around obstacles, and check out Keyi’s thread for more details!

Yunzhu Li

10,561 次观看 • 1 年前

Helix neural network

Helix neural network

Brett Adcock

69,292 次观看 • 1 年前

#BestPaperAwardHonorableMention #SIGGRAPH2025 One neural PDE model, hundreds of cuts and discontinuities — simulated in real time. 🚀 Introducing WindLifter: lifting the winding number fields lets us capture discontinuities in neural fields. Come see ChangYue’s talk today 👉

#BestPaperAwardHonorableMention #SIGGRAPH2025 One neural PDE model, hundreds of cuts and discontinuities — simulated in real time. 🚀 Introducing WindLifter: lifting the winding number fields lets us capture discontinuities in neural fields. Come see ChangYue’s talk today 👉

Peter Yichen Chen

11,483 次观看 • 10 个月前