The world’s leading publication for data science, AI, and ML professionals.

Checking out dimensionality reduction with t-SNE

Today I explored applying t-SNE on two high-dimension datasets: the classic MNIST and the nouveau fashionMNIST.

Today I explored applying t-SNE on two high-dimension datasets: the classic MNIST and the nouveau fashionMNIST.

You can read all about fashionMNIST here which is set out to be MNIST scaled up in complexity.

While MNIST contains handwritten digits from 0 to 9, fashionMNIST contains 10 different kinds of attires from t-shirts to dresses to trousers.

I ran t-SNE on the entire original MNIST training set, which is rather well-separated, and compared it with fashionMNIST.

MNIST in 2D
MNIST in 2D

And observed some overlapping in fashionMNIST.

fashionMNIST in 3D
fashionMNIST in 3D

We can further rotate it in plotly and remove the clearly separately classes to identify the overlapping classes: t-shirt, shirt and coat.


This is #day53 of my #100dayprojects on Data Science and visual storytelling. Full code on my github. Thanks for reading. Suggestions of new topics and feedbacks are always welcomed.


Related Articles