This is a t-SNE I made a couple of years ago of the glove-wordvectors for numbers. So it’s not surprising that there is a “number sense”, though I am definitely surprised how good some of the results are.
Fun fact: Fitting the Iris dataset with a tiny neural network can be suprisingly fickle.
This is a t-SNE I made a couple of years ago of the glove-wordvectors for numbers. So it’s not surprising that there is a “number sense”, though I am definitely surprised how good some of the results are.
Fun fact: Fitting the Iris dataset with a tiny neural network can be suprisingly fickle.