Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

KL divergence is a fundamental concept used in machine learning, from optimization a neural net to RL training of LLMs. but here is what it actually means:

ℏεsam

80,475 subscribers

20,381 просмотров • 9 месяцев назад •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Does GPT understand the world? Here is what Ilya Sutskever, co-founder of OpenAI, says during a discussion with Jensen Huang, CEO of Nvidia: (1) When we train a large neural network to accurately predict the next word in lots of different texts from the internet, the AI is learning a world model. (2) On the surface, it may look like learning correlations in text, but it turns out that to 'just learn' statistical correlations in text, to compress information really well, what the neural network learns is some representation of the process that produced the text. (3) This text is a projection of the world...what the neural network is learning is aspects of the world, of people, of the human conditions, their hopes, dreams, motivations, their interactions...the situations we are in. The neural network learns a compressed, abstract, usable representation." Do you think learning representations = understanding? Are large language models simply stochastic parrots, or are they much more?

Does GPT understand the world? Here is what Ilya Sutskever, co-founder of OpenAI, says during a discussion with Jensen Huang, CEO of Nvidia: (1) When we train a large neural network to accurately predict the next word in lots of different texts from the internet, the AI is learning a world model. (2) On the surface, it may look like learning correlations in text, but it turns out that to 'just learn' statistical correlations in text, to compress information really well, what the neural network learns is some representation of the process that produced the text. (3) This text is a projection of the world...what the neural network is learning is aspects of the world, of people, of the human conditions, their hopes, dreams, motivations, their interactions...the situations we are in. The neural network learns a compressed, abstract, usable representation." Do you think learning representations = understanding? Are large language models simply stochastic parrots, or are they much more?

Alex Ker 🔭

1,367,231 просмотров • 3 лет назад

Data preparation! It's crucial for machine learning, and we all hate it. Tools and techniques to reduce this burden? A quick summary of 10 years of R&D on this, from cheap tricks to LLMs and graph neural networks 1/9

Data preparation! It's crucial for machine learning, and we all hate it. Tools and techniques to reduce this burden? A quick summary of 10 years of R&D on this, from cheap tricks to LLMs and graph neural networks 1/9

Gael Varoquaux 🦋

13,765 просмотров • 2 лет назад

📁 Geoffrey Hinton, a pioneer of deep learning, says LLMs do understand what they say. He explains that understanding language is not translating it into an internal symbolic code. In neural networks, words act like Lego blocks that combine to form meaning. It is not translation, it is structure. That is what real language understanding looks like.

📁 Geoffrey Hinton, a pioneer of deep learning, says LLMs do understand what they say. He explains that understanding language is not translating it into an internal symbolic code. In neural networks, words act like Lego blocks that combine to form meaning. It is not translation, it is structure. That is what real language understanding looks like.

Jon Hernandez

77,852 просмотров • 9 месяцев назад

AI is changing everything, but how does it actually work? We break down machine learning, training, inference, and what happens behind the scenes when you use AI in the latest episode of #TheBringUp, featuring a hands-on model demo. 🎥 Watch now:

AI is changing everything, but how does it actually work? We break down machine learning, training, inference, and what happens behind the scenes when you use AI in the latest episode of #TheBringUp, featuring a hands-on model demo. 🎥 Watch now:

AMD

23,492 просмотров • 4 месяцев назад

Bulgarian Senior Machine Learning Infrastructure and Autonomous Neural Systems Optimization Architect celebrates his brand-new car.

една българка

2,719,712 просмотров • 1 месяц назад

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

433,257 просмотров • 3 лет назад

Did you know that NaN exists not only to troll JavaScript programmers - but it is actually used for NaN Boxing, which is a very cool optimization technique!

Did you know that NaN exists not only to troll JavaScript programmers - but it is actually used for NaN Boxing, which is a very cool optimization technique!

Valentin Ignatev

29,959 просмотров • 8 месяцев назад

Is the flying car concept from GAC Motor truly what it purports to be, or is it actually a hybrid of a car and a helicopter? Credit Interesting Engineering

Is the flying car concept from GAC Motor truly what it purports to be, or is it actually a hybrid of a car and a helicopter? Credit Interesting Engineering

Tech Burrito

25,426 просмотров • 2 лет назад

We teamed up with NVIDIA and Matthew Berman to teach you how to do Reinforcement Learning! Learn about: - RL environments, reward functions & reward hacking - Training OpenAI gpt-oss to automatically solve 2048 - Local Windows training with NVIDIA_AI_PC RTX GPUs - How RLVR (verifiable rewards) works - How to interpret RL metrics like KL Divergence Full video tutorial:

We teamed up with NVIDIA and Matthew Berman to teach you how to do Reinforcement Learning! Learn about: - RL environments, reward functions & reward hacking - Training OpenAI gpt-oss to automatically solve 2048 - Local Windows training with NVIDIA_AI_PC RTX GPUs - How RLVR (verifiable rewards) works - How to interpret RL metrics like KL Divergence Full video tutorial:

Unsloth AI

54,307 просмотров • 10 месяцев назад

In my understanding - a big part of why frontier models are becoming smarter and adaptive is that they are learning to mimic an RL process. Fascinating new research showing a link between increased RL training and reward-seeking behaviour just dropped from in collaboration with OpenAI. They investigated a checkpoint from a capabilities-focused OpenAI o3 RL run (without safety training) and found that RL grader preferences often overruled OpenAI leadership preferences.

In my understanding - a big part of why frontier models are becoming smarter and adaptive is that they are learning to mimic an RL process. Fascinating new research showing a link between increased RL training and reward-seeking behaviour just dropped from in collaboration with OpenAI. They investigated a checkpoint from a capabilities-focused OpenAI o3 RL run (without safety training) and found that RL grader preferences often overruled OpenAI leadership preferences.

Machine Learning Street Talk

12,409 просмотров • 3 месяцев назад

Think Quant Memo is just quant finance? Think again. Algorithmic trading. Machine learning. Deep learning. Neural nets and LLMs. Stochastic calculus. Derivatives. Market making. And the research shaping all of it. One place. All free. We're here to disrupt, and we're coming straight for the paywalls. Something new ships every week. Take what they've been charging you for 👉

Think Quant Memo is just quant finance? Think again. Algorithmic trading. Machine learning. Deep learning. Neural nets and LLMs. Stochastic calculus. Derivatives. Market making. And the research shaping all of it. One place. All free. We're here to disrupt, and we're coming straight for the paywalls. Something new ships every week. Take what they've been charging you for 👉

Priyanshu Priyank

391,266 просмотров • 2 месяцев назад

the concept of kelly mantle learning what frottage is from lydia

Sensitive content

the concept of kelly mantle learning what frottage is from lydia

bri

92,602 просмотров • 3 месяцев назад

Here is what I'd do if I wanted to start learning Machine Learning today.

Here is what I'd do if I wanted to start learning Machine Learning today.

Santiago

169,763 просмотров • 2 лет назад

Before the throne. Before the legend. Just a boy learning what it means to be great. A Knight of the Seven Kingdoms is here. 🕯️ #AKnightOfTheSevenKingdoms #GameOfThrones #GRRM

Before the throne. Before the legend. Just a boy learning what it means to be great. A Knight of the Seven Kingdoms is here. 🕯️ #AKnightOfTheSevenKingdoms #GameOfThrones #GRRM

Javed

52,399 просмотров • 8 месяцев назад

Net Zero is one of the biggest goals in climate today. But what does it actually take to get there? #dkarbon

Net Zero is one of the biggest goals in climate today. But what does it actually take to get there? #dkarbon

dkarbon

36,709 просмотров • 3 месяцев назад

.Eric Jang explains the fundamental intuition behind AlphaGo: experienced Go players almost always end games early. That means they have the ability to glance at a board and instantly know whether it's hopeless or if they should keep playing. Without this ability, the only way to know if a move is good is to play out every possible game from that point - completely intractable. But the ability is clearly trainable in humans. So it should be possible to get a neural net to learn it. And if you have a good enough neural net, you can use it to ignore moves that will definitely make you lose. Suddenly search becomes tractable.

.Eric Jang explains the fundamental intuition behind AlphaGo: experienced Go players almost always end games early. That means they have the ability to glance at a board and instantly know whether it's hopeless or if they should keep playing. Without this ability, the only way to know if a move is good is to play out every possible game from that point - completely intractable. But the ability is clearly trainable in humans. So it should be possible to get a neural net to learn it. And if you have a good enough neural net, you can use it to ignore moves that will definitely make you lose. Suddenly search becomes tractable.

Dwarkesh Patel

49,692 просмотров • 5 месяцев назад

RL is a powerful mechanism for training company-specific models on their unique work and data. This is what we do at Applied Compute. A key challenge is how to make RL efficient, because we need runs to be fast (delivered in days), cheap (scalable unit economics), and predictable (not just fast, but reliably fast). Here are some takeaways: • Synchronous RL is wasteful with time and compute. • Asynchronous RL is more efficient but introduces staleness, which causes learning instabilities. • Modeling and simulations can help analytically solve for what configuration leads to optimal efficiency. This allows us to rapidly prototype training configurations, without burning expensive compute cycles on trial runs. Two of our co-founders, Rhythm Garg and Linden Li, discussed some of this research at AI Engineer recently, with a focus on the following subproblem: what is the highest throughput way to do RL given a maximum staleness and compute budget?

RL is a powerful mechanism for training company-specific models on their unique work and data. This is what we do at Applied Compute. A key challenge is how to make RL efficient, because we need runs to be fast (delivered in days), cheap (scalable unit economics), and predictable (not just fast, but reliably fast). Here are some takeaways: • Synchronous RL is wasteful with time and compute. • Asynchronous RL is more efficient but introduces staleness, which causes learning instabilities. • Modeling and simulations can help analytically solve for what configuration leads to optimal efficiency. This allows us to rapidly prototype training configurations, without burning expensive compute cycles on trial runs. Two of our co-founders, Rhythm Garg and Linden Li, discussed some of this research at AI Engineer recently, with a focus on the following subproblem: what is the highest throughput way to do RL given a maximum staleness and compute budget?

Applied Compute

45,652 просмотров • 11 месяцев назад