Playing with fonts using neural networks

Posted to Statistics  |  Tags: ,  |  Nathan Yau

Erik Bernhardsson downloaded 50,000 fonts and then threw them to the neural networks to see what sort of letters a model might come up with.

These are all characters drawn from the test set, so the network hasn’t seen any of them during training. All we’re telling the network is (a) what font it is (b) what character it is. The model has seen other characters of the same font during training, so what it does is to infer from those training examples to the unseen test examples.

I especially like the part where you can see a spectrum of generated fonts through varying parameters.

Favorites

A Day in the Life of Americans

I wanted to see how daily patterns emerge at the individual level and how a person’s entire day plays out. So I simulated 1,000 of them.

Where Bars Outnumber Grocery Stores

A closer look at the age old question of where there are more bars than grocery stores, and vice versa.

Divorce Rates for Different Groups

We know when people usually get married. We know who never marries. Finally, it’s time to look at the other side: divorce and remarriage.

Real Chart Rules to Follow

There are rules—usually for specific chart types meant to be read in a specific way—that you shouldn’t break. When they are, everyone loses. This is that small handful.