The big picture
Four ideas to keep.
| Idea | Remember |
|---|---|
| The data science loop | Collect and clean the data. Train a model. Improve it with fresh data. |
| Data that fits the question | A data-driven answer needs data that matches the question. |
| How a computer sees | A vision system usually tidies the picture first. Then it finds features, and names, locates or follows objects. |
| How a computer reads | NLP cuts text into words and tidies them. Then it works out grammar and meaning. |
Each kind of data has its own steps. Ask what the data is, then ask which step comes next.