The typical "hello world" example for ML is a classifier trained over the MNIST dataset; a dataset of the handwritten digits 0-9. This dataset is getting a little stale and is no longer impressive with employers as a proof of capability due to both its seeming simplicity and to the plethora of existing tutorials on the topic. Here we will use a newer dataset to perform our ML "hello world", the Fashion MNIST dataset!
The Fashion MNIST dataset is comprised of 70,000 grayscale images of articles of clothing. The greyscale values for a pixel range from 0-255 (black to white). Each low-resolution image is 28x28 pixels and is of exactly one clothing item. Alongside each image is a label that places the article within a category; these categories are shown in Figure 2 with an example image belonging to the class.
Figure 2 class numbers are shown next to image labels