Three kinds of machine learning problems
In all our previous examples, we tried to solve either classification (predicting cats or dogs) or regression (predicting the average time users spend in the platform) problems. All these are examples of supervised learning, where the goal is to map the relationship between training examples and their targets and use it to make predictions on unseen data.
Supervised learning is just one part of machine learning, and there are other different parts of machine learning. There are three different kinds of machine learning:
- Supervised learning
- Unsupervised learning
- Reinforcement learning
Let's look in detail at the kinds of algorithms.
Supervised learning
Most of the successful use cases in the deep learning and machine learning space fall under supervised learning. Most of the examples we cover in this book will also be part of this. Some of the common examples of supervised learning are:
- Classification problems: Classifying dogs and cats.
- Regression problems...
