Mohamad Wahba

Just enrolled in the 2025 𝐃𝐚𝐭𝐚 𝐄𝐧𝐠𝐢𝐧𝐞𝐞𝐫𝐢𝐧𝐠 𝐙𝐨𝐨𝐦𝐜𝐚𝐦𝐩 by DataTalksClub! 🚀

Can't wait to explore data engineering and grow with an amazing cohort. Big shoutout to DataTalksClub for this awesome opportunity!

#DataEngineering #LearningInPublic

For those who don’t feel like they fit into my Grumpy Machine Learners list (which I still need to update based on 100+ requests) I’ve created another starter pack:

go.bsky.app/Js7ka12

(Self) nominations welcome.

The Ultimate Guide to PyTorch Contributions Tensors and Dynamic neural networks in Python with strong GPU acceleration - pytorch/pytorch

For those who wonder about the best way to start contributing to pytorch or open-source projects, here are the top three pointers I'd share:

1. The Ultimate Guide to PyTorch Contributions github.com/pytorch/pyto...
For pytorch core that should be the n1 item on your list.

Training variance is a thing and no one measures it because research models get trained once to beat the benchmark by 0.2 AP or whatever and then never trained again.

In prod one of the first things we do is train (the same model) a ton over different shuffled splits of the data in order to… 1/3

You know the "🔹AI Overview" you get on Google Search?

I discovered today that it's repeating as fact something I made up 7 years ago as a joke.

"Kyloren syndrome" is a fictional disease I invented as part of a sting operation to prove that you can publish any nonsense in predatory journals...

Here's a walk-through of a general-purpose approach to solving many types of optimization problem. It's often not the most efficient way, but it is often fast enough, and it doesn't require using different methods for different problems.
youtu.be/U2b5Cacertc

Book outline

Over the past decade, embeddings — numerical representations of machine learning features used as input to deep learning models — have become a foundational data structure in industrial machine learning systems. TF-IDF, PCA, and one-hot encoding have always been key tools in machine learning systems as ways to compress and make sense of large amounts of textual data. However, traditional approaches were limited in the amount of context they could reason about with increasing amounts of data. As the volume, velocity, and variety of data captured by modern applications has exploded, creating approaches specifically tailored to scale has become increasingly important. Google’s Word2Vec paper made an important step in moving from simple statistical representations to semantic meaning of words. The subsequent rise of the Transformer architecture and transfer learning, as well as the latest surge in generative methods has enabled the growth of embeddings as a foundational machine learning data structure. This survey paper aims to provide a deep dive into what embeddings are, their history, and usage patterns in industry.

Cover image

Just realized BlueSky allows sharing valuable stuff cause it doesn't punish links. 🤩

Let's start with "What are embeddings" by @vickiboykis.com

The book is a great summary of embeddings, from history to modern approaches.

The best part: it's free.

Link: vickiboykis.com/what_are_emb...