What is machine learning?
One definition that I think captures very well the intuition behind machine learning comes from Andrew Ng, adjunct professor at Stanford University, in his Machine Learning class on Coursera (https://www.coursera.org/learn/machine-learning):
Machine learning is the science of getting computers to learn, without being explicitly programmed.
The key word from the preceding definition is learn, which, in this context, has a meaning that is very similar to how, we, humans learn. To continue with this parallel, from a young age, we were taught how to accomplish a task either by example, or on our own by trial and error. Broadly speaking, machine learning algorithms can be categorized into two types that correspond to the two ways in which humans learn:
- Supervised: The algorithm learns from example data that has been properly labeled. This data is also called training data, or sometimes referred to as ground truth.
- Unsupervised: The algorithm is able...
