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。

A practical example for how deep learning models struggle with out-of-distribution data.

ℏεsam

39,730 subscribers

24,616 次观看 • 1 年前 •via X (Twitter)

科学技术教育

Anya Rossi• Live Now

Private livecam show

10 条评论

Lorenz S. 的头像

Lorenz S.1 年前

Read the actual road markings. It has nothing to do with out-of-distribution data but with legal driving. This is certainly not out-of-distribution for Tesla.

Polygon.io 的头像

Polygon.io2 年前

Learn how to access market data using Polygon's Stock API and the Python programming language.

Okabe 的头像

Okabe1 年前

Bro it ain’t even driving itself using FSD

Oleg Pavlov 的头像

Oleg Pavlov1 年前

No it's not. It just doesn't know what 3d model to choose from, cause apparently there's no 3d model for a carriage.

Ash 的头像

Ash1 年前

Not entirely accurate, this is quite an old footage, before FSD even started e2e models, also ODD is not a deep learning model issue but a training issue if this was even the case here

𝕄waura 的头像

𝕄waura1 年前

Looks like an old duck, moves like a duck then it must be a DUCK

Captain Jack 的头像

Captain Jack1 年前

@HuoQubot

The MF Pretty 的头像

The MF Pretty1 年前

Not sure if its a struggle.. Do you want it to go "Fuck it, no idea what it is, run them over"?

Sciumo 的头像

Sciumo1 年前

LoL @Tesla went schizo

Marcus Fordham 的头像

Marcus Fordham1 年前

Lol based Mennonites

相关视频

Learn to train an LLM with distributed data while ensuring privacy using federated learning in a new two-part short course, Intro to Federated Learning and Federated Fine-tuning of LLMs with Private Data, created with Flower and taught by Daniel J. Beutel and nic lane. Federated learning allows a single model to be trained across multiple devices, such as phones, or multiple organizations, such as hospitals, without the need to share data to a central server. This two-part course gives you an introduction to federated learning, and then teaches you how to fine-tune your large language model with distributed data using Flower Lab’s open source federated learning framework. You’ll learn: - How to use federated learning to train a variety of models, ranging from speech and vision models to LLMs, across distributed data while offering data privacy options to users and organizations. - Privacy Enhancing Technologies like differential privacy (DP), which obscures individual data by adding calibrated noise to query results. - Two variants of differential privacy - Central and Local - and how to choose depending on your use case. - How to measure and decrease bandwidth usage to make federated learning more practical and efficient with techniques like using pre-trained models and Parameter-Efficient Fine-Tuning - How federated LLM fine-tuning reduces the risk of leaking training data. Sign up here!

Learn to train an LLM with distributed data while ensuring privacy using federated learning in a new two-part short course, Intro to Federated Learning and Federated Fine-tuning of LLMs with Private Data, created with Flower and taught by Daniel J. Beutel and nic lane. Federated learning allows a single model to be trained across multiple devices, such as phones, or multiple organizations, such as hospitals, without the need to share data to a central server. This two-part course gives you an introduction to federated learning, and then teaches you how to fine-tune your large language model with distributed data using Flower Lab’s open source federated learning framework. You’ll learn: - How to use federated learning to train a variety of models, ranging from speech and vision models to LLMs, across distributed data while offering data privacy options to users and organizations. - Privacy Enhancing Technologies like differential privacy (DP), which obscures individual data by adding calibrated noise to query results. - Two variants of differential privacy - Central and Local - and how to choose depending on your use case. - How to measure and decrease bandwidth usage to make federated learning more practical and efficient with techniques like using pre-trained models and Parameter-Efficient Fine-Tuning - How federated LLM fine-tuning reduces the risk of leaking training data. Sign up here!

Andrew Ng

64,558 次观看 • 1 年前

Curious whether video generation models (like #SORA) qualify as world models? We conduct a systematic study to answer this question by investigating whether a video gen model is able to learn physical laws. Three are three key messages to take home: 1⃣The model generalises perfectly for in-distribution data, but fails to do out-of-distribution generalization. For combinatorial scenarios, scaling law is observed. 2⃣The models fail to abstract general rules and instead tries to mimic the closest training example. 3⃣The model prioritizes different attributes when referencing training data: color > size > velocity > shape. This work is a joint effort with our outstanding intern Yang Yue@ICML 7.7-7.9. Paper: Webpage:

Curious whether video generation models (like #SORA) qualify as world models? We conduct a systematic study to answer this question by investigating whether a video gen model is able to learn physical laws. Three are three key messages to take home: 1⃣The model generalises perfectly for in-distribution data, but fails to do out-of-distribution generalization. For combinatorial scenarios, scaling law is observed. 2⃣The models fail to abstract general rules and instead tries to mimic the closest training example. 3⃣The model prioritizes different attributes when referencing training data: color > size > velocity > shape. This work is a joint effort with our outstanding intern Yang Yue@ICML 7.7-7.9. Paper: Webpage:

Bingyi Kang

606,630 次观看 • 1 年前

🚀 GeoAI Tutorial 23: Building Detection from Aerial Imagery and LiDAR Data 🏙️🛰️ In this tutorial, I demonstrate how to train a deep learning segmentation model for building detection by combining aerial/satellite imagery with LiDAR data. You'll learn how to fuse multi-source remote sensing data to improve model accuracy and robustness. 🔗 Tutorial video: 📓 Notebook example: 💻 GitHub repo: 📚 Documentation: 🎥 Full playlist: #GeoAI #geospatial #AI #Python #DeepLearning

🚀 GeoAI Tutorial 23: Building Detection from Aerial Imagery and LiDAR Data 🏙️🛰️ In this tutorial, I demonstrate how to train a deep learning segmentation model for building detection by combining aerial/satellite imagery with LiDAR data. You'll learn how to fuse multi-source remote sensing data to improve model accuracy and robustness. 🔗 Tutorial video: 📓 Notebook example: 💻 GitHub repo: 📚 Documentation: 🎥 Full playlist: #GeoAI #geospatial #AI #Python #DeepLearning

Qiusheng Wu

12,194 次观看 • 1 年前

Learning how to play Melee with ADHD How to deal with opponents who play far away from you Plenty of Melee players struggle with ADD/ADHD and I want to start a series breaking down specific types of interactions or playstyles that we struggle with

Learning how to play Melee with ADHD How to deal with opponents who play far away from you Plenty of Melee players struggle with ADD/ADHD and I want to start a series breaking down specific types of interactions or playstyles that we struggle with

Justus

101,129 次观看 • 1 年前

Over the last few months, we’ve been thinking about how to learn from “off-domain” data - data from non-robot sources like video or simulation. These data sources are not quite good enough to learn policies (even monolithic VLA models) directly, but they still contain lots of information that can be useful for generalizable robot control. How can we develop robot learning models that are able to make use of this type of data for generalizable control? In new work, that we call HAMSTER, we show that VLMs can be useful for enabling robotic learning from off-domain data, but specifically when used through hierarchical VLA architectures. We show that this class of models can learn generalizable robot policies for the real world from large-scale, off-domain data. A 🧵 (1/10)

Over the last few months, we’ve been thinking about how to learn from “off-domain” data - data from non-robot sources like video or simulation. These data sources are not quite good enough to learn policies (even monolithic VLA models) directly, but they still contain lots of information that can be useful for generalizable robot control. How can we develop robot learning models that are able to make use of this type of data for generalizable control? In new work, that we call HAMSTER, we show that VLMs can be useful for enabling robotic learning from off-domain data, but specifically when used through hierarchical VLA architectures. We show that this class of models can learn generalizable robot policies for the real world from large-scale, off-domain data. A 🧵 (1/10)

Abhishek Gupta

11,994 次观看 • 1 年前

News: ChatGPT's Deep Research for free! Courtesy of lighter weight models :) 🆕 No Priors with OpenAI's Isa Fulford on: *how they built it (and improve it) *what data we need to train better agents *agents going from read --> write, safety *how she uses Deep Research herself

News: ChatGPT's Deep Research for free! Courtesy of lighter weight models :) 🆕 No Priors with OpenAI's Isa Fulford on: how they built it (and improve it) what data we need to train better agents agents going from read --> write, safety how she uses Deep Research herself

sarah guo

43,729 次观看 • 1 年前

Foundation models, machine learning, and #AI use cases. In this episode of Smart Talks with IBM hosted by Malcolm Gladwell, IBM Research VP of AI Models explores the future of AI and data platforms like #watsonx with Jacob Goldstein:

Foundation models, machine learning, and #AI use cases. In this episode of Smart Talks with IBM hosted by Malcolm Gladwell, IBM Research VP of AI Models explores the future of AI and data platforms like #watsonx with Jacob Goldstein:

IBM

27,078 次观看 • 2 年前

World models hold a lot of promise for robotics, but they're data hungry and often struggle with long horizons. We learn models from a few (< 10) human demos that enable a robot to plan in completely novel scenes! Our key idea is to model *symbols* not pixels 👇

World models hold a lot of promise for robotics, but they're data hungry and often struggle with long horizons. We learn models from a few (< 10) human demos that enable a robot to plan in completely novel scenes! Our key idea is to model symbols not pixels 👇

Nishanth Kumar

82,931 次观看 • 10 个月前

Robot foundation models are limited by costly real data, while simulation data is plentiful but visually mismatched to reality. We present Point Bridge, a method that enables zero-shot sim-to-real transfer for robot learning with minimal visual alignment.

Robot foundation models are limited by costly real data, while simulation data is plentiful but visually mismatched to reality. We present Point Bridge, a method that enables zero-shot sim-to-real transfer for robot learning with minimal visual alignment.

Siddhant Haldar

19,862 次观看 • 4 个月前

Over 60 key digital reference titles for researchers and faculty in Big Data, Deep Learning, Federated Learning, Medical Technology, Pattern Recognition, Quantum Computing, and more. Find out more at and recommend it to your library!

Over 60 key digital reference titles for researchers and faculty in Big Data, Deep Learning, Federated Learning, Medical Technology, Pattern Recognition, Quantum Computing, and more. Find out more at and recommend it to your library!

World Scientific

64,925 次观看 • 10 个月前

Introducing ESM Cambrian. Unsupervised learning can invert biology at scale to reveal the hidden structure of the natural world. We’ve scaled up compute and data to train a new generation of protein language models. ESM C defines a new state of the art for protein representation learning.

Introducing ESM Cambrian. Unsupervised learning can invert biology at scale to reveal the hidden structure of the natural world. We’ve scaled up compute and data to train a new generation of protein language models. ESM C defines a new state of the art for protein representation learning.

Alex Rives

206,851 次观看 • 1 年前

Φ-SO : Physical Symbolic Optimization - Learning Physics from Data 🧠 The Physical Symbolic Optimization package uses deep reinforcement learning to discover physical laws from data. Here is Φ-SO discovering the analytical expression of a damped harmonic oscillator.

Φ-SO : Physical Symbolic Optimization - Learning Physics from Data 🧠 The Physical Symbolic Optimization package uses deep reinforcement learning to discover physical laws from data. Here is Φ-SO discovering the analytical expression of a damped harmonic oscillator.

Jousef Murad

433,149 次观看 • 2 年前

The drawing table from the 1930s, is a beautiful example of the engineering thought of that time with thoughtful and practical functionality.

The drawing table from the 1930s, is a beautiful example of the engineering thought of that time with thoughtful and practical functionality.

The Figen

62,394 次观看 • 8 个月前

as an example for learning...

as an example for learning...

Kaerariyaa

2,763,172 次观看 • 2 天前

Real World example of how individual location can be found from advertising data

Real World example of how individual location can be found from advertising data

Unplugged

45,232 次观看 • 10 个月前

Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning investigated the application of Deep Reinforcement Learning (Deep RL) for low-cost, miniature humanoid hardware in a dynamic environment, showing the method can synthesize sophisticated and safe movement skills making up complex behavioral strategies in a simplified one-versus-one (1v1) soccer game abs: project page:

Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning investigated the application of Deep Reinforcement Learning (Deep RL) for low-cost, miniature humanoid hardware in a dynamic environment, showing the method can synthesize sophisticated and safe movement skills making up complex behavioral strategies in a simplified one-versus-one (1v1) soccer game abs: project page:

AK

293,339 次观看 • 3 年前

ELECTION NIGHT: HUNTINGTON BEACH I will make life less of a struggle for working people & small businesses. Simple, practical changes for Californians ☀️

ELECTION NIGHT: HUNTINGTON BEACH I will make life less of a struggle for working people & small businesses. Simple, practical changes for Californians ☀️

Steve Hilton

22,787 次观看 • 1 个月前

Revolutionizing Move Programming with OpenLedger In this demo, we showcase how Move datasets contributed by data providers to OpenLedger’s datanets are used to fine-tune specialized models with LoRA fine-tuning. As seen in the video, we showcase an example on how builders can deploy a Move-specialized model that powers Co-pilot agents using our no-code model fine-tuning platform. This is the future of AI and Web3 innovation. Watch this space to see more specialised models and data feeds being built for next generation agents on top of OpenLedger #Move

Revolutionizing Move Programming with OpenLedger In this demo, we showcase how Move datasets contributed by data providers to OpenLedger’s datanets are used to fine-tune specialized models with LoRA fine-tuning. As seen in the video, we showcase an example on how builders can deploy a Move-specialized model that powers Co-pilot agents using our no-code model fine-tuning platform. This is the future of AI and Web3 innovation. Watch this space to see more specialised models and data feeds being built for next generation agents on top of OpenLedger #Move

OpenLedger

61,662 次观看 • 1 年前