Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

New video series: Physics Informed Machine Learning! Physics may be embedded into AI/ML in 5 stages: 1 choose what to Model 2 curate training Data 3 design an Architecture 4 craft a Loss Function, and 5 implement Optimization Algorithm to train the model

Steven Brunton

55,759 subscribers

78,432 Aufrufe • vor 2 Jahren •via X (Twitter)

Wissenschaft & Technologie Bildung

Anya Rossi• Live Now

Private livecam show

10 Kommentare

Profilbild von vik

vikvor 2 Jahren

love the production quality on this!

Profilbild von James O'Reilly

James O'Reillyvor 2 Jahren

Watched this in bed last night, absolutely fascinating stuff @eigensteve. These are exciting times for us engineers in the commercial space. Change is happening fast! I'm excited for the rest of these sessions.

Profilbild von deewakar

deewakarvor 2 Jahren

Started working on this few months ago. This was amazing as usual. Looking forward for DeepOnets

Profilbild von 𝕽𝖎𝖙𝖔 𝕲𝖍𝖔𝖘𝖍 (𝖊/λ🧠⚗️🧑🏻‍💻)

𝕽𝖎𝖙𝖔 𝕲𝖍𝖔𝖘𝖍 (𝖊/λ🧠⚗️🧑🏻‍💻)vor 2 Jahren

Waiting for the next video, already!

Profilbild von VivaDoyers

VivaDoyersvor 2 Jahren

Thanks Professor. Love your videos and will be watching this one!

Profilbild von Stefano

Stefanovor 2 Jahren

“Welcome back”

Profilbild von Prach na knihovně

Prach na knihovněvor 2 Jahren

That's great! Love your work! Greetings from the Central Europe!

Profilbild von kasim guventurk

kasim guventurkvor 2 Jahren

Thank you for the great content Professor. I am so grateful.

Profilbild von Serendipity

Serendipityvor 2 Jahren

cant wait!

Profilbild von Johan Botha

Johan Bothavor 2 Jahren

Thanks, Steve Although I haven't watched the complete series the parts I have watched are brilliant. Just a question how would this relate to Cyber-Physical Systems

Ähnliche Videos

In case you missed it, we recently launched "Post-training of LLMs," a short course where you'll: ✅ Understand when and why to use post-training methods like Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning. ✅ Learn the concepts underlying the three post-training methods of SFT, DPO, and Online RL, their common use-cases, and how to curate high-quality data to effectively train a model using each method. ✅ Download a pre-trained model and implement post-training pipelines to turn a base model into an instruct model, change the identity of a chat assistant, and improve a model’s math capabilities. Learn more and enroll for free:

In case you missed it, we recently launched "Post-training of LLMs," a short course where you'll: ✅ Understand when and why to use post-training methods like Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning. ✅ Learn the concepts underlying the three post-training methods of SFT, DPO, and Online RL, their common use-cases, and how to curate high-quality data to effectively train a model using each method. ✅ Download a pre-trained model and implement post-training pipelines to turn a base model into an instruct model, change the identity of a chat assistant, and improve a model’s math capabilities. Learn more and enroll for free:

DeepLearning.AI

16,746 Aufrufe • vor 11 Monaten

Excited to share that our paper 🌊🤺 “CFC: Simulating Character–Fluid Coupling using a Two-Level World Model” has been accepted to #SIGGRAPHASIA2025! In this work, we build a two-level world model (neural physics) for rigid-body–fluid interaction and use it to train physics-based character controllers efficiently. We study: (1) learning to model highly dynamic fluid environments, (2) representing character–fluid interaction via joint-level forces as an interface, and (3) enabling supervised policy learning on the learned world model—avoiding expensive fluid simulation in the training loop. Our talk is on Monday afternoon(Dec 15)—hope to see you there! Time: Monday, 15 December 2025 5:02pm - 5:13pm GMT+8 Location: Meeting Room S221, Level 2. #SIGGRAPHASIA #SIGGRAPH

Excited to share that our paper 🌊🤺 “CFC: Simulating Character–Fluid Coupling using a Two-Level World Model” has been accepted to #SIGGRAPHASIA2025! In this work, we build a two-level world model (neural physics) for rigid-body–fluid interaction and use it to train physics-based character controllers efficiently. We study: (1) learning to model highly dynamic fluid environments, (2) representing character–fluid interaction via joint-level forces as an interface, and (3) enabling supervised policy learning on the learned world model—avoiding expensive fluid simulation in the training loop. Our talk is on Monday afternoon(Dec 15)—hope to see you there! Time: Monday, 15 December 2025 5:02pm - 5:13pm GMT+8 Location: Meeting Room S221, Level 2. #SIGGRAPHASIA #SIGGRAPH

Zhiyang (Frank) Dou

20,200 Aufrufe • vor 6 Monaten

Data curation is crucial for post-training recipes. But how do we curate? Curation is usually manual & tedious. And, it's hard to tell if a strategy in the data will be reliable! We introduce an automatic way to curate, informed by the robot's policy learning.

Data curation is crucial for post-training recipes. But how do we curate? Curation is usually manual & tedious. And, it's hard to tell if a strategy in the data will be reliable! We introduce an automatic way to curate, informed by the robot's policy learning.

Chelsea Finn

19,910 Aufrufe • vor 1 Jahr

Our course recommendation of the day is “Post-training of LLMs, ” where you’ll learn how to customize pre-trained language models using Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning (RL). You'll learn when to use each method, how to curate training data, and implement them in code to shape model behavior effectively. Enroll here:

Our course recommendation of the day is “Post-training of LLMs, ” where you’ll learn how to customize pre-trained language models using Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning (RL). You'll learn when to use each method, how to curate training data, and implement them in code to shape model behavior effectively. Enroll here:

DeepLearning.AI

29,369 Aufrufe • vor 8 Monaten

“Enterprises should probably never train an AI model.” In this episode of our AI Explainer Series, Sr. Product Marketing Manager for AI, Meena Ganesh, and Box CTO, Ben Kus explain the challenges enterprises will face with training a model, and then explore why the smarter path is a combination of AI agents + RAG. Timestamps: 1:07 Reasons why enterprises shouldn't train a model 1:24 What it means to train a model 2:36 Explaining the concept of fine-tuning 4:50 Privacy challenges: AI doesn't keep secrets 6:40 What can enterprises do? 9:48 How enterprises can choose the right path

“Enterprises should probably never train an AI model.” In this episode of our AI Explainer Series, Sr. Product Marketing Manager for AI, Meena Ganesh, and Box CTO, Ben Kus explain the challenges enterprises will face with training a model, and then explore why the smarter path is a combination of AI agents + RAG. Timestamps: 1:07 Reasons why enterprises shouldn't train a model 1:24 What it means to train a model 2:36 Explaining the concept of fine-tuning 4:50 Privacy challenges: AI doesn't keep secrets 6:40 What can enterprises do? 9:48 How enterprises can choose the right path

Box

354,042 Aufrufe • vor 6 Monaten

📢 New short course in collaboration with Google: Build and Train an LLM with JAX. In this course, you’ll implement and train a 20M-parameter MiniGPT-style language model from scratch using JAX, the open-source library behind Gemini. You’ll build the model architecture, load and preprocess training data, implement the training loop, save checkpoints, and generate text through a chat interface. Taught by Chris Achard, Developer Relations Engineer on Google’s TPU Software team. Enroll now:

📢 New short course in collaboration with Google: Build and Train an LLM with JAX. In this course, you’ll implement and train a 20M-parameter MiniGPT-style language model from scratch using JAX, the open-source library behind Gemini. You’ll build the model architecture, load and preprocess training data, implement the training loop, save checkpoints, and generate text through a chat interface. Taught by Chris Achard, Developer Relations Engineer on Google’s TPU Software team. Enroll now:

DeepLearning.AI

46,065 Aufrufe • vor 3 Monaten

Archetype AI published a new paper demonstrating how an AI model can encode and predict physical behaviours. Newton, the startup's ‘Large Behavior Model’, can learn complex physics principles directly from raw sensor data, without any human guidance.

Archetype AI published a new paper demonstrating how an AI model can encode and predict physical behaviours. Newton, the startup's ‘Large Behavior Model’, can learn complex physics principles directly from raw sensor data, without any human guidance.

Brett Adcock

25,958 Aufrufe • vor 1 Jahr

An interactive world model developed by NVIDIA in collaboration with academic partners. - DreamDojo turns egocentric human video data into physical intelligence. - Human data is more scalable than robotics data but lacks action labels. - To solve this, a dedicated action model extracts latent actions by identifying physics and motion deltas between frames. Training - A massive 44k hours of video data are used for pre-training. - Post-training on small-scale robot datasets maps human physics to specific robot embodiments. - An additional distillation stage converts the model into an autoregressive, few-step diffusion model, enabling real-time, action-controllable simulation. Primary Use Cases - Live Teleoperation: Controlling a robot inside a world simulation in real-time. - Model-based Planning: Previewing and curating the best actions for improved success. - Policy Evaluation: Testing robot policies in realistic, out-of-distribution scenarios. Everything that's open-sourced: weights, code, post-training dataset, eval set, and details to reproduce.

An interactive world model developed by NVIDIA in collaboration with academic partners. - DreamDojo turns egocentric human video data into physical intelligence. - Human data is more scalable than robotics data but lacks action labels. - To solve this, a dedicated action model extracts latent actions by identifying physics and motion deltas between frames. Training - A massive 44k hours of video data are used for pre-training. - Post-training on small-scale robot datasets maps human physics to specific robot embodiments. - An additional distillation stage converts the model into an autoregressive, few-step diffusion model, enabling real-time, action-controllable simulation. Primary Use Cases - Live Teleoperation: Controlling a robot inside a world simulation in real-time. - Model-based Planning: Previewing and curating the best actions for improved success. - Policy Evaluation: Testing robot policies in realistic, out-of-distribution scenarios. Everything that's open-sourced: weights, code, post-training dataset, eval set, and details to reproduce.

The Humanoid Hub

11,575 Aufrufe • vor 3 Monaten

if you're struggling on where to start learning ML, here’s a playlist of 30 youtube videos to learn machine learning fundamentals from scratch "Machine Learning: Teach by Doing" is a solid choice to learn both theory and code. (1) Introduction to Machine Learning Teach by Doing: (2) What is Machine Learning? History of Machine Learning: (3) Types of ML Models: (4) 6 steps of any ML project: (5) Install Python and VSCode and run your first code: (6) Linear Classifiers Part 1: (7) Linear Classifiers Part 2: (8) Jupyter Notebook, Numpy and Scikit-Learn: (9) Running the Random Linear Classifier Algorithm in Python: (10) The oldest ML model - Perceptron: (11) Coding the Perceptron: (12) Perceptron Convergence Theorem: (13) Magic of features in Machine Learning: (14) One hot encoding: (15) Logistic Regression Part 1: (16) Cross Entropy Loss: (17) How gradient descent works: (18) Logistic Regression from scratch in Python: (19) Introduction to Regularization: (20) Implementing Regularization in Python: (21) Linear Regression Introduction: (22) Ordinary Least Squares step by step implementation: (23) Ridge regression fundamentals and intuition: (24) Regression recap for interviews: (25) Neural network architecture in 30 minutes: (26) Backpropagation intuition: (27) Neural network activation functions: (28) Momentum in gradient descent: (29) Hands on neural network training in Python: (30) Introduction to Convolutional Neural Networks (CNNs):

if you're struggling on where to start learning ML, here’s a playlist of 30 youtube videos to learn machine learning fundamentals from scratch "Machine Learning: Teach by Doing" is a solid choice to learn both theory and code. (1) Introduction to Machine Learning Teach by Doing: (2) What is Machine Learning? History of Machine Learning: (3) Types of ML Models: (4) 6 steps of any ML project: (5) Install Python and VSCode and run your first code: (6) Linear Classifiers Part 1: (7) Linear Classifiers Part 2: (8) Jupyter Notebook, Numpy and Scikit-Learn: (9) Running the Random Linear Classifier Algorithm in Python: (10) The oldest ML model - Perceptron: (11) Coding the Perceptron: (12) Perceptron Convergence Theorem: (13) Magic of features in Machine Learning: (14) One hot encoding: (15) Logistic Regression Part 1: (16) Cross Entropy Loss: (17) How gradient descent works: (18) Logistic Regression from scratch in Python: (19) Introduction to Regularization: (20) Implementing Regularization in Python: (21) Linear Regression Introduction: (22) Ordinary Least Squares step by step implementation: (23) Ridge regression fundamentals and intuition: (24) Regression recap for interviews: (25) Neural network architecture in 30 minutes: (26) Backpropagation intuition: (27) Neural network activation functions: (28) Momentum in gradient descent: (29) Hands on neural network training in Python: (30) Introduction to Convolutional Neural Networks (CNNs):

ℏεsam

108,861 Aufrufe • vor 1 Jahr

a playlist of 30 youtube videos to learn machine learning fundamentals from scratch if you're struggling on where to start learning ML, this list goes this "Machine Learning: Teach by Doing" is a solid choice to learn both theory and code. (1) Introduction to Machine Learning Teach by Doing: (2) What is Machine Learning? History of Machine Learning: (3) Types of ML Models: (4) 6 steps of any ML project: (5) Install Python and VSCode and run your first code: (6) Linear Classifiers Part 1: (7) Linear Classifiers Part 2: (8) Jupyter Notebook, Numpy and Scikit-Learn: (9) Running the Random Linear Classifier Algorithm in Python: (10) The oldest ML model - Perceptron: (11) Coding the Perceptron: (12) Perceptron Convergence Theorem: (13) Magic of features in Machine Learning: (14) One hot encoding: (15) Logistic Regression Part 1: (16) Cross Entropy Loss: (17) How gradient descent works: (18) Logistic Regression from scratch in Python: (19) Introduction to Regularization: (20) Implementing Regularization in Python: (21) Linear Regression Introduction: (22) Ordinary Least Squares step by step implementation: (23) Ridge regression fundamentals and intuition: (24) Regression recap for interviews: (25) Neural network architecture in 30 minutes: (26) Backpropagation intuition: (27) Neural network activation functions: (28) Momentum in gradient descent: (29) Hands on neural network training in Python: (30) Introduction to Convolutional Neural Networks (CNNs):

a playlist of 30 youtube videos to learn machine learning fundamentals from scratch if you're struggling on where to start learning ML, this list goes this "Machine Learning: Teach by Doing" is a solid choice to learn both theory and code. (1) Introduction to Machine Learning Teach by Doing: (2) What is Machine Learning? History of Machine Learning: (3) Types of ML Models: (4) 6 steps of any ML project: (5) Install Python and VSCode and run your first code: (6) Linear Classifiers Part 1: (7) Linear Classifiers Part 2: (8) Jupyter Notebook, Numpy and Scikit-Learn: (9) Running the Random Linear Classifier Algorithm in Python: (10) The oldest ML model - Perceptron: (11) Coding the Perceptron: (12) Perceptron Convergence Theorem: (13) Magic of features in Machine Learning: (14) One hot encoding: (15) Logistic Regression Part 1: (16) Cross Entropy Loss: (17) How gradient descent works: (18) Logistic Regression from scratch in Python: (19) Introduction to Regularization: (20) Implementing Regularization in Python: (21) Linear Regression Introduction: (22) Ordinary Least Squares step by step implementation: (23) Ridge regression fundamentals and intuition: (24) Regression recap for interviews: (25) Neural network architecture in 30 minutes: (26) Backpropagation intuition: (27) Neural network activation functions: (28) Momentum in gradient descent: (29) Hands on neural network training in Python: (30) Introduction to Convolutional Neural Networks (CNNs):

ℏεsam

117,570 Aufrufe • vor 1 Jahr

Meet Hybrid: an EVM-compatible Layer 1 blockchain enriched with specialized data layers for AI, and home to Atlas, our machine learning model, designed to deliver intuitive AI-driven analytics. A thread 👇

Meet Hybrid: an EVM-compatible Layer 1 blockchain enriched with specialized data layers for AI, and home to Atlas, our machine learning model, designed to deliver intuitive AI-driven analytics. A thread 👇

Hybrid

543,981 Aufrufe • vor 2 Jahren

Data is the foundation of any AI training. All of the GPUs in the world can't train an AI model if they don't have data to train it on. Don't forget: Grass is the data layer of AI.

Data is the foundation of any AI training. All of the GPUs in the world can't train an AI model if they don't have data to train it on. Don't forget: Grass is the data layer of AI.

Grass

211,905 Aufrufe • vor 2 Jahren

1/ 🤖 New paper hot off the press 🐜 Automated behavioural analysis using machine learning is great, but still needs lots of effort to curate training data. What if a computer could generate that data for you? Say hello to replicAnt #OpenSource

1/ 🤖 New paper hot off the press 🐜 Automated behavioural analysis using machine learning is great, but still needs lots of effort to curate training data. What if a computer could generate that data for you? Say hello to replicAnt #OpenSource

Evolutionary Biomechanics Laboratory

54,805 Aufrufe • vor 2 Jahren

Building a machine learning model isn’t just about finding the right algorithm—it’s about the right process. In Machine Learning in Production, Andrew Ng breaks down the iterative loop of model development: training, error analysis, refining hyperparameters, and improving data. Getting to a high test set accuracy is one thing, but aligning your model with real-world business metrics? That’s where the real challenge begins. Learn how to bridge the gap between models and impact:

Building a machine learning model isn’t just about finding the right algorithm—it’s about the right process. In Machine Learning in Production, Andrew Ng breaks down the iterative loop of model development: training, error analysis, refining hyperparameters, and improving data. Getting to a high test set accuracy is one thing, but aligning your model with real-world business metrics? That’s where the real challenge begins. Learn how to bridge the gap between models and impact:

DeepLearning.AI

45,248 Aufrufe • vor 1 Jahr

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

433,091 Aufrufe • vor 2 Jahren

ELON MUSK: "It's incredibly important for AI model to be grounded in reality. Reality, you know, physics is the law and everything else is a recommendation. For AI to really be intelligent it's got to make predictions that are inline with reality, in other words, physics."

ELON MUSK: "It's incredibly important for AI model to be grounded in reality. Reality, you know, physics is the law and everything else is a recommendation. For AI to really be intelligent it's got to make predictions that are inline with reality, in other words, physics."

DogeDesigner

71,708 Aufrufe • vor 6 Monaten

I'm excited to introduce my AI Machine Learning Agent that built 32 ML models in 30 seconds. Today, I'll share with you how to automate building 100s of ML models with the AI ML Agent, which is available on GitHub. We'll create an ML Agent focusing on a Customer Churn Problem. I'll guide you through setting up the ML Agent, creating dozens of ML models, and loading the best model for production. This AI is a huge time-saver! Table of Contents: 00:00 Introduction to my AI Data Science Team 02:56 Setting Up AI Data Science Team 04:48 Running the ML Agent Code 07:12 Create (and Run) the AI Machine Learning Agent 09:53 Reviewing ML Model Summary 12:00 Saving and Loading Models 13:00 Next Steps + Project Roadmap + AI Bootcamp Github to AI Data Science Team (Data Science Agents): Get the Code and Future Updates by Joining my Python AI/ML Tips Newsletter: P.S. - Want to learn how to build AI projects companies actually want? (live Python Code) On Wednesday, May 21st, I'm sharing one of my best AI Projects: AI Customer Segmentation Agent with Python Register here (570+ registered):

I'm excited to introduce my AI Machine Learning Agent that built 32 ML models in 30 seconds. Today, I'll share with you how to automate building 100s of ML models with the AI ML Agent, which is available on GitHub. We'll create an ML Agent focusing on a Customer Churn Problem. I'll guide you through setting up the ML Agent, creating dozens of ML models, and loading the best model for production. This AI is a huge time-saver! Table of Contents: 00:00 Introduction to my AI Data Science Team 02:56 Setting Up AI Data Science Team 04:48 Running the ML Agent Code 07:12 Create (and Run) the AI Machine Learning Agent 09:53 Reviewing ML Model Summary 12:00 Saving and Loading Models 13:00 Next Steps + Project Roadmap + AI Bootcamp Github to AI Data Science Team (Data Science Agents): Get the Code and Future Updates by Joining my Python AI/ML Tips Newsletter: P.S. - Want to learn how to build AI projects companies actually want? (live Python Code) On Wednesday, May 21st, I'm sharing one of my best AI Projects: AI Customer Segmentation Agent with Python Register here (570+ registered):

Matt Dancho (Business Science)

35,428 Aufrufe • vor 1 Jahr

New Course: Post-training of LLMs Learn to post-train and customize an LLM in this short course, taught by Banghua Zhu, Assistant Professor at the University of Washington University of Washington, and co-founder of @NexusflowX. Training an LLM to follow instructions or answer questions has two key stages: pre-training and post-training. In pre-training, it learns to predict the next word or token from large amounts of unlabeled text. In post-training, it learns useful behaviors such as following instructions, tool use, and reasoning. Post-training transforms a general-purpose token predictor—trained on trillions of unlabeled text tokens—into an assistant that follows instructions and performs specific tasks. Because it is much cheaper than pre-training, it is practical for many more teams to incorporate post-training methods into their workflows than pre-training. In this course, you’ll learn three common post-training methods—Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning (RL)—and how to use each one effectively. With SFT, you train the model on pairs of input and ideal output responses. With DPO, you provide both a preferred (chosen) and a less preferred (rejected) response and train the model to favor the preferred output. With RL, the model generates an output, receives a reward score based on human or automated feedback, and updates the model to improve performance. You’ll learn the basic concepts, common use cases, and principles for curating high-quality data for effective training. Through hands-on labs, you’ll download a pre-trained model from Hugging Face and post-train it using SFT, DPO, and RL to see how each technique shapes model behavior. In detail, you’ll: - Understand what post-training is, when to use it, and how it differs from pre-training. - Build an SFT pipeline to turn a base model into an instruct model. - Explore how DPO reshapes behavior by minimizing contrastive loss—penalizing poor responses and reinforcing preferred ones. - Implement a DPO pipeline to change the identity of a chat assistant. - Learn online RL methods such as Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO), and how to design reward functions. - Train a model with GRPO to improve its math capabilities using a verifiable reward. Post-training is one of the most rapidly developing areas of LLM training. Whether you’re building a high-accuracy context-specific assistant, fine-tuning a model's tone, or improving task-specific accuracy, this course will give you experience with the most important techniques shaping how LLMs are post-trained today. Please sign up here:

New Course: Post-training of LLMs Learn to post-train and customize an LLM in this short course, taught by Banghua Zhu, Assistant Professor at the University of Washington University of Washington, and co-founder of @NexusflowX. Training an LLM to follow instructions or answer questions has two key stages: pre-training and post-training. In pre-training, it learns to predict the next word or token from large amounts of unlabeled text. In post-training, it learns useful behaviors such as following instructions, tool use, and reasoning. Post-training transforms a general-purpose token predictor—trained on trillions of unlabeled text tokens—into an assistant that follows instructions and performs specific tasks. Because it is much cheaper than pre-training, it is practical for many more teams to incorporate post-training methods into their workflows than pre-training. In this course, you’ll learn three common post-training methods—Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning (RL)—and how to use each one effectively. With SFT, you train the model on pairs of input and ideal output responses. With DPO, you provide both a preferred (chosen) and a less preferred (rejected) response and train the model to favor the preferred output. With RL, the model generates an output, receives a reward score based on human or automated feedback, and updates the model to improve performance. You’ll learn the basic concepts, common use cases, and principles for curating high-quality data for effective training. Through hands-on labs, you’ll download a pre-trained model from Hugging Face and post-train it using SFT, DPO, and RL to see how each technique shapes model behavior. In detail, you’ll: - Understand what post-training is, when to use it, and how it differs from pre-training. - Build an SFT pipeline to turn a base model into an instruct model. - Explore how DPO reshapes behavior by minimizing contrastive loss—penalizing poor responses and reinforcing preferred ones. - Implement a DPO pipeline to change the identity of a chat assistant. - Learn online RL methods such as Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO), and how to design reward functions. - Train a model with GRPO to improve its math capabilities using a verifiable reward. Post-training is one of the most rapidly developing areas of LLM training. Whether you’re building a high-accuracy context-specific assistant, fine-tuning a model's tone, or improving task-specific accuracy, this course will give you experience with the most important techniques shaping how LLMs are post-trained today. Please sign up here:

Andrew Ng

125,146 Aufrufe • vor 11 Monaten

🚨 ELON MUSK: "It's incredibly important for AI model to be grounded in reality. Reality, you know, physics is the law and everything else is a recommendation. For AI to really be intelligent it's got to make predictions that are inline with reality, in other words, physics."

🚨 ELON MUSK: "It's incredibly important for AI model to be grounded in reality. Reality, you know, physics is the law and everything else is a recommendation. For AI to really be intelligent it's got to make predictions that are inline with reality, in other words, physics."

DogeDesigner

1,130,340 Aufrufe • vor 1 Jahr