/explore

Click through on any links that interest you or select the planets on the right to continue exploring the Outer Web.
You are here

 lambdalabs.com
OpenAI's GPT-3 Language Model: A Technical Overview
| | jaykmody.com
GPT in 60 Lines of NumPy | Jay Mody
1.8 parsecs away

Travel
| | Implementing a GPT model from scratch in NumPy.
| | blog.miguelgrinberg.com
How LLMs Work, Explained Without Math - miguelgrinberg.com
1.4 parsecs away

Travel
| | miguelgrinberg.com
| | blog.moonglow.ai
Three Kuhnian Revolutions in ML Training
1.7 parsecs away

Travel
| | Parameters and data. These are the two ingredients of training ML models. The total amount of computation ("compute") you need to do to train a model is proportional to the number of parameters multiplied by the amount of data (measured in "tokens"). Four years ago, it was well-known that if
| | jaketae.github.io
Convolutional Neural Network with Keras - Jake Tae
12.6 parsecs away

Travel
| Recently, a friend recommended me a book, Deep Learning with Python by Francois Chollet. As an eager learner just starting to fiddle with the Keras API, I decided it was a good starting point. I have just finished the first section of Part 2 on Convolutional Neural Networks and image processing. My impression so far is that the book is more focused on code than math. The apparent advantage of this approach is that it shows readers how to build neural networks very transparently. It's also a good introduction to many neural network models, such as CNNs or LSTMs. On the flip side, it might leave some readers wondering why these models work, concretely and mathematically. This point notwithstanding, I've been enjoying the book very much so far, and this post is...