Backpropagation Applied to Handwritten Zip Code Recognition
This code tries to reproduce the 1989 Yann LeCun et al. paper: Backpropagation Applied to Handwritten Zip Code Recognition. To my knowledge this is the earliest real-world application of a neural net trained with backpropagation (now 33 years ago).
run
Since we don’t have the exact dataset that was used in the paper, we take MNIST and randomly pick examples from it to generate an approximation of the dataset, which contains only 7291 training and 2007 testing digits, only of size 16×16 pixels (standard MNIST is 28×28).
Now we can attempt to reproduce the paper. The original network trained for 3 days, but my (Apple Silicon M1) MacBook Air 33 years later chunks through it in about 90 seconds. (non-emulated arm64 but CPU only, I don’t believe