When a system learns to translate text, it can compare its outputs with known translations. This is supervised learning: a machine-learning approach that maps labeled inputs to desired outputs. section 1.1
Labels identify the desired answer for each training example. Human experts often define these answers, making data preparation potentially labor-intensive. Unlike unsupervised learning, supervised learning uses labels; unlike reinforcement learning, it does not rely primarily on trial-and-error rewards or penalties. section 1.1
Table 1.1 Types of machine learning
| Supervised learning |
Unsupervised learning |
Reinforcement learning |
|
| Description |
The model learns by mapping labeled inputs to known outputs. |
The model is trained without labels and without a specific reward. |
The model learns from its environment based on rewards and penalties. |
| Data |
Labeled data |
Unlabeled data |
No static dataset |
| Objective |
To predict the output of unseen inputs |
To discover underlying patterns in the data, such as clusters |
To determine the optimal strategy via trial and error |
Compare supervised, unsupervised, and reinforcement learning by their data, objectives, and learning signals. section 1.1
