AI engineering glossary · ML fundamentals
What is overparameterisation?
Overparameterisation (also called Overparametrization): Having more adjustable parameters in a model than training examples. Such models can fit the training data perfectly, yet modern large networks often still generalise well, in part because of how training methods steer toward simpler solutions.
Overparameterisation: an example
A network with 10 million weights trained on 50,000 images is heavily overparameterised in this sense.
Related terms
More ML fundamentals terms
- PAC learning
- Parameter
- Parametric model
- Pipeline
- Probabilistic model
- Problem framing
- Random search
- Random seed
Where you learn it
Overparameterisation is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.