AI engineering glossary · ML fundamentals
What is parameter?
Parameter (also called Weights): A number inside a model that is learned from data during training, such as a weight in a linear equation. The learning algorithm adjusts parameters to reduce error. Their values, not the code around them, hold what the model has learned.
Parameter: an example
In price = 2.5 x area + 40, the values 2.5 and 40 are parameters fitted from data.
Related terms
More ML fundamentals terms
- Parametric model
- Pipeline
- Probabilistic model
- Problem framing
- Random search
- Random seed
- Regression
- Regularisation
Where you learn it
Parameter is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.