Based on our record, Neural Networks and Deep Learning seems to be a lot more popular than Facebook.ai. While we know about 44 links to Neural Networks and Deep Learning, we've tracked only 2 mentions of Facebook.ai. We are tracking product recommendations and mentions on various public social media platforms and blogs. They can help you identify which product is more popular and what people think of it.
For neural network theory, I'm very fond of http://neuralnetworksanddeeplearning.com, but you'll need calculus and some linear algebra to understand it. Source: 5 months ago
Alternatively, building them from scratch in numpy is definitely possible and an excellent way to learn the fundamentals. It will take some time though (debugging issues with a hand-rolled LSTM is very, very painful). There's a zillion tutorials/books out there (I think I started with http://neuralnetworksanddeeplearning.com). Source: 5 months ago
- http://neuralnetworksanddeeplearning.com/ The Watch the Caltech telecourse. - Source: Hacker News / 8 months ago
Neural Networks and Deep Learning, a free online book. http://neuralnetworksanddeeplearning.com/. - Source: Hacker News / 9 months ago
Many years ago I was studying deep learning using this resource: * http://neuralnetworksanddeeplearning.com/ I decided to try to implement everything from scratch in Elixir (after initially doing all the math with pen and paper on a trivial example to get the feel of it). Obviously pure elixir was extremely slow, so I started creating NIFs to pass over matrix multiplication to OpenBLAS. Then I was thinking more... - Source: Hacker News / 11 months ago
Many settings affect the outputs in interesting ways, but that's half the fun. These LoRAs are very lightly trained; more training may or may not help. The competitions are also performed using zero-shot text guessing, and if Facebook said it, you can bet that's actually Meta AI saying it, and they are leaders in the field. Source: about 1 year ago
You should look at the entire niche of MAE-related papers, that's quite exciting, and the neuroscience-inspired stream of stuff like Barlow Twins. As well, the official Facebook AI blog is surprisingly good coverage of much of the interesting un/semi-supervised DL research FAIR does, and worth going through. Source: over 1 year ago
Colornet - Neural Network to colorize grayscale images
A.I. Experiments by Google - Explore machine learning by playing w/ pics, music, and more
Quick Draw Game - Can a neural network learn to recognize doodles?
Lobe - Visual tool for building custom deep learning models
AETROS - Create, train and monitor deep neural networks
Deep Learning Gallery - A curated list of awesome deep learning projects