Everything you care about in one place
Follow feeds: blogs, news, RSS and more. An effortless way to read and digest content of your choice.
Get Feedereli.thegreenplace.net
Eli Bendersky's website
Get the latest updates from Eli Bendersky's website directly as they happen.
Follow now 244 followers
Latest posts
Last updated 1 day ago
Sparsely-gated Mixture Of Experts (MoE)
1 day ago
In transformer models, the attention block is typically followed by a feed...
Cross-entropy and KL divergence
8 days ago
Cross-entropy is widely used in modern ML to compute the loss for...
Reproducing word2vec with JAX
15 days ago
The word2vec model was proposed in a 2013 paper by Google researchers...
Summary of reading: January - March 2025
19 days ago
"The Birth of Britain: A History of the English Speaking Peoples, Volume...
Notes on implementing Attention
24 days ago
Some notes on implementing attention blocks in pure Python + Numpy. The...
Understanding Numpy's einsum
29 days ago
This is a brief explanation and a cookbook for using numpy.einsum which...
Making any integer with four 2s
about 2 months ago
There's a cute math puzzle that can be interesting to folks on...
Benchmarking utility for Python
2 months ago
Go programmers have it pretty good with the benchmarking capabilities provided by...
Decorator JITs - Python as a DSL
3 months ago
Spend enough time looking at Python programs and packages for machine learning...
Reverse mode Automatic Differentiation
3 months ago
Automatic Differentiation (AD) is an important algorithm for calculating the derivatives of...
Summary of reading: October - December 2024
4 months ago
"Dr. Euler's Fabulous Formula" by Paul J. Nahin - a kind of...
Implementing Raft: Part 5 - exactly-once delivery
4 months ago
This is Part 5 in a series of posts describing the Raft...