howtolearnmach1's profile picture. The Machine Learning Sensei

Merlin🦉

@howtolearnmach1

The Machine Learning Sensei

Pinned

My goal at How to Learn Machine Learning is to guide everybody through the best resources in this vast world, to learn, enjoy, and discover Machine Learning and Artificial Intelligence 🦉🤖🥷 🧑‍🏫 🧠Check out our blog 📚 💻 howtolearnmachinelearning.com


Merlin🦉 reposted

This is literally the book trusted by Stanford, MIT, and Google to teach AI

hayesdev_'s tweet image. This is literally the book trusted by Stanford, MIT, and Google to teach AI

Superintelligence by Ray Kurzweil: how to create ASI and have roombas rule the world! Check out my full review before your blender joins the AI uprising 🛡️🤖⚔️ howtolearnmachinelearning.com/books/artifici…


Merlin🦉 reposted

We keep scaling model parameters by increasing width and stacking more layers, but what if the truly missing axes for continual learning are compression and stacking the learning process? Excited to share the full version of Nested Learning, a new paradigm for continual learning…

behrouz_ali's tweet image. We keep scaling model parameters by increasing width and stacking more layers, but what if the truly missing axes for continual learning are compression and stacking the learning process?

Excited to share the full version of Nested Learning, a new paradigm for continual learning…

Merlin🦉 reposted

it took time, but the blogs are finally taking shape. one at a time.

saurabhtwq's tweet image. it took time, but the blogs are finally taking shape. one at a time.

Merlin🦉 reposted

RL is back, baby! Here's a course to get you started 𝗖𝗼𝗻𝘁𝗲𝘅𝘁 Reinforcement Learning (RL) is one of the key ingredients to post-train Language Models for long, complex tasks, hard-for-humans tasks, especially with verifiable rewards. For example, maths or coding, which is…

paulabartabajo_'s tweet image. RL is back, baby! Here's a course to get you started

𝗖𝗼𝗻𝘁𝗲𝘅𝘁

Reinforcement Learning (RL) is one of the key ingredients to post-train Language Models for long, complex tasks, hard-for-humans tasks, especially with verifiable rewards. For example, maths or coding, which is…

Merlin🦉 reposted

This paper really is groundbreaking. It solves a long-standing embarrassment in machine learning: despite all the hype around deep learning, traditional tree-based methods (XGBoost, CatBoost, random forests, etc) have dominated tabular data—the most common data format in…

burkov's tweet image. This paper really is groundbreaking. It solves a long-standing embarrassment in machine learning: despite all the hype around deep learning, traditional tree-based methods (XGBoost, CatBoost, random forests, etc) have dominated tabular data—the most common data format in…

Merlin🦉 reposted

this is big... 50 AI researchers from Bytedance, Alibaba, Tencent, and other labs/universities just published a 300-page paper with surprising lessons about coding models and agents (data, pre and post-training, etc). key highlights: > small LLMs can beat proprietary giants RL…

Hesamation's tweet image. this is big... 50 AI researchers from Bytedance, Alibaba, Tencent, and other labs/universities just published a 300-page paper with surprising lessons about coding models and agents (data, pre and post-training, etc). key highlights:

> small LLMs can beat proprietary giants
RL…

Merlin🦉 reposted

Interesting paper Title. "What the F*ck Is Artificial General Intelligence?" It defines intelligence as adaptability under limits of compute, memory, and energy. So AGI is a system that adapts at least as generally as a human scientist That means it should be able to plan…

rohanpaul_ai's tweet image. Interesting paper Title.

"What the F*ck Is Artificial General Intelligence?"

It defines intelligence as adaptability under limits of compute, memory, and energy.

So AGI is a system that adapts at least as generally as a human scientist

That means it should be able to plan…

Lets rock the day!


Merlin🦉 reposted

your laziness is disrespectful for the people who believe in you :

hamptonism's tweet image. your laziness is disrespectful for the people who believe in you :

Merlin🦉 reposted

she talks about a critical learning mistake nobody really talks about. you shouldn’t just manage your time, but also your energy. here’s how: > your attention is a budget, spend it wisely and when you’re most energized (early morning, late night, etc. notice your energy patterns.…

Hesamation's tweet image. she talks about a critical learning mistake nobody really talks about. you shouldn’t just manage your time, but also your energy. here’s how:
> your attention is a budget, spend it wisely and when you’re most energized (early morning, late night, etc. notice your energy patterns.…

Merlin🦉 reposted

New @GoogleDeepMind paper builds a new benchmark and agent design so language models can actually learn from their own experience. Right now most language model agents only keep chat logs or facts, so they remember what happened but not how to solve similar tasks better, and the…

rohanpaul_ai's tweet image. New @GoogleDeepMind paper builds a new benchmark and agent design so language models can actually learn from their own experience.

Right now most language model agents only keep chat logs or facts, so they remember what happened but not how to solve similar tasks better, and the…

Merlin🦉 reposted

This is my list of 20 research papers, which I read for LLMs [Not in some days, guys]. If you want to read some of them or all of them, I'm attaching the drive link here. Excel sheet: docs.google.com/spreadsheets/d… Or you just search the paper name, and you will find a link to it.…

techwith_ram's tweet image. This is my list of 20 research papers, which I read for LLMs [Not in some days, guys]. If you want to read some of them or all of them, I'm attaching the drive link here.

Excel sheet: docs.google.com/spreadsheets/d…

Or you just search the paper name, and you will find a link to it.…

Merlin🦉 reposted

i still believe this repo is the best roadmap to learning LLMs. it’s designed by a solid expert and covers three paths for: > LLM fundamentals > LLM scientist > LLM engineer you can start from scratch and learn the math, ml, architecture, theory, and code behind LLMs with free…

Hesamation's tweet image. i still believe this repo is the best roadmap to learning LLMs. it’s designed by a solid expert and covers three paths for:
> LLM fundamentals 
> LLM scientist
> LLM engineer
you can start from scratch and learn the math, ml, architecture, theory, and code behind LLMs with free…

I love you all <3


Have a great day all :)


Loading...

Something went wrong.


Something went wrong.