About us
Stay in touch
A dataset of 70,000 handwritten digits, released in 1998 and long the standard first test for machine-learning models.
The first thing that I trained was taking little images of handwritten digits from a data set called MNIST that's really overused in machine learning research, but it's also very fast to train on.
Ian Goodfellow, Ian Goodfellow on Inventing GANs
With Boltzmann Machines, you spend quite a lot of time struggling to get them to produce recognizable MNIST digits. This just went ahead and spat out MNIST digits in two minutes.
Ian Goodfellow, Ian Goodfellow on Inventing GANs