By Daniel Geng and Shannon Shih:

So what is Machine Learning?

At its core, machine learning is not a difficult concept to grasp. In fact, the vast majority of machine learning algorithms are concerned with just one simple task: drawing lines. In particular, machine learning is all about drawing lines through data. What does that mean? Let’s look at a simple example.

Classification

Let’s say you’re a computer with a collection of apple and orange images. From each image you can infer the color and size of a fruit, and you want to classify the images as either an image of an apple or an orange. The first step in many machine learning algorithms is to obtain labeled training data. In our example, this means getting a large number of images of fruit each labeled as either being an apple or an orange. From these images, we can extract the color and size information and then see how they correlate with being an apple or an orange. For example, graphing our labeled training data might look like something this: