Kepler was a Data Scientist

With the blooming of machine learning that has occurred over the past decade, the notion of machines that learn from experience has become a mainstream theme in both technical and journalistic circles. Now, how is it exactly that a machine learns? What are the mechanics of it, or the algorithm behind it? From the point of view of an outer observer, a learning algorithm is presented input data that is paired with desired outputs. When learning has occurred, that algorithm is capable of producing correct outputs when it’s fed new data that is similar enough to the input data on which it was trained. With deep learning, this process works even when the input data and the desired output are far from each other — when they come from different domains, such as an image and a sentence describing it.

As a matter of fact, models that allow you to explain input/output relationships date back centuries. When Johannes Kepler, a German mathematical astronomer who lived between 1571 and 1630, figured out his three laws of planetary motion in the early 1600s, he based them on data collected by his mentor, Tycho Brahe, during naked-eye observations (yep, naked eye and a piece of paper). Not having Newton’s Law of gravitation at his disposal (in fact, Newton used Kepler’s work to figure things out), he extrapolated the simplest possible geometric model that could fit the data. By the way, it took him six years…