In plain English
Models turn things into lists and tables of numbers. Similar things have close numbers. Averages, probability and the idea of stepping downhill to lower an error cover most of the maths you meet. Use AI tools with common sense. Study more only when you want to build models.
- Vector
- A list of numbers that stands for something.
- Probability
- A number from 0 to 1 for how likely something is.
- Gradient descent
- Learning by small steps that lower the error.
Picture it
How a model learns by stepping downhill
1
Measure the error
How wrong is it now?
2