Taxonomy of machine learning techniques

The discussion in the previous section should have helped you understand the reason behind the ML paradigm. However, it only corresponds to one type of learning. ML algorithms can be trained differently, with each method having advantages and disadvantages. Broadly, they can be categorized into four main types: supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning. Let’s examine each one in the following sections.

Supervised learning

In supervised learning, also called inductive learning, we work with labeled data that teaches the model to yield the desired output. For example, a dataset with emails labeled as either spam or non-spam can be used to train a model for spam filtering. It’s called supervised because by knowing the correct label for each sample, we can supervise the learning process and correct the model during training, just like a teacher in the classroom. This type...