Concept dictionary
Parameters
Parameters are the adjustable numerical values a model uses to transform inputs into outputs; many are learned during training.
- Review state
- Reviewed in POC
- Freshness
- Current
- Version
- 2
Also called
- Parameters
- Model Parameters
Remember it this wayParameters are the model's adjustable internal values.
In plain language
Training changes model parameters so the system performs better according to its training objective. Parameter count describes one aspect of model size, not the quality of the whole system.
Why it matters
Parameter counts are often used in product comparisons, but architecture, data, training, tools, and evaluation can matter as much or more for a specific task.
Example
A model described as having billions of parameters contains billions of adjustable values distributed across its learned structure.
Common misconception
More parameters do not automatically mean a model is more accurate, safer, more efficient, or better suited to a particular use.
Related terms
Sources
- Google for Developers, Machine Learning Glossarytechnical definition of model parameters and related training concepts.
Learn more
- Relate parameter count to [[weights|Weights]] and efficiency work such as [[model-distillation|Model Distillation]].