Machine Learning
1297 Threads
Recap! Our 3 most popular posts on time-series: — 5 TS concepts you should know about — 3 open-source frameworks for TS forecasting — TS forecasting is a key component of Uber’s M...
Do you think that cutting-edge Deep Learning models developed by some of the brightest AI researchers in the world, like @DeepMind Perceiver, are bullet-proof systems, that are imp...
@bg_learning The most helpful thing for me has been a wide variety of datasets, models, applications in prod. But it has also been useful to have a basic understanding of linalg wh...
I don't think I've ever talked about this online, but the best ML-in-prod people I know have crazy good intuition for different classes of models can & can't do. We don't yet have...
It’s out! Oh boy! Probabilistic Numerics: big ideas for the internals of learning machines — and now also a BOOK, w/ @maosbot and @HansKersting! What is #ProbabilisticNumerics,...
7 powerful machine learning techniques everyone should know (with links to Python code):
One of my fave chapters of "Practical Deep Learning for Coders", co-written with @GuggerSylvain, is chapter 8. I've just made the whole thing available as an executable notebook on...
🤖 What is Overfitting In Machine Learning? 🤔 A statistical model is said to be overfitted when we feed it a lot more data than necessary. To make it relatable, imagine trying to f...
ROC curves are a topic that you will encounter at some point in your machine learning journey. They are one the most important metrics for evaluating a model. Let's how they work...
📚 Explain the terms #ArtificialIntelligence (AI), #MachineLearning (ML) and #DeepLearning (DL) ?📚 🧵👇 https://t.co/6MUFSz1BbI
21 most valuable Github Repositories for Data Science & Machine learning 🧵🧵🧵
Google spent $36,847 an hour for 40 days straight to train a machine learning model called AlphaGo. Put simply, making these models is an expensive and lengthy process. Here's h...
We have successfully trained OpenFold from scratch, our trainable PyTorch implementation of AlphaFold2. The new OpenFold (OF) (slightly) outperforms AlphaFold2 (AF2). I believe thi...
Learn for free: HTML: https://t.co/ZZ65CzGLB4 CSS: https://t.co/f9C247W2fy JavaScript: https://t.co/b1EUNxLUhi React: https://t.co/GeXp4JaWic Vue: https://t.co/FrY6gZoJfW Git: htt...
Honestly: sometimes I feel defeated because ML observability is so hard. All facets are hard -- detecting, diagnosing, reacting to bugs. We don't have realtime ground truth labels...
Tutorials completely failed to teach me how machine learning works. I used to just import scikit-learn and call https://t.co/hu5TFSsBsR. So I spent 100 hours studying the most po...
The Hello World! of machine learning: Classifying handwriting digits. But everyone solves this problem the same way. Here is a different, non-boring approach that you haven't see...
Protein structure can be predicted from a single sequence alone with high accuracy. @HelixonBio team have developed OmegaFold, achieving performance similar to RF and AF2's MSA ve...
After talking to many machine learning engineers, only those at the top use this technique to train their models. Distribute training makes a world of difference. And contrary t...
We now finally have the thing I've always wanted: an analysis of the best vision models for finetuning. In joint work with @capetorch we tried nearly 100 models on two very differ...
Wanna learn how to train better ML models, by finding and fixing issues in your data? At the speed of light? Let's see how in this mega 🧵 #data #machinelearning
nvt op Tuesday! 🥳 Today we have a very special guest on our show! 🍾 The "Grandmaster Special" 😄 Many a competition has been won with its help, but the devil lies in the implement...
🤖What is the History of #ArtificialIntelligence❓ https://t.co/D8HO4hN7eQ #AI #DataScience #Bigdata #Analytics #MachineLearning #ML #Python #RStats #Fintech #IoT #TensorFlow #Digi...
[🧠Chinchilla "Training Compute-Optimal Large Language Models" paper summary] Key idea: all of our LLMs so far have been undertrained - for a given compute (FLOPs) and model size...
