AI glossary · Machine learning
Parameters
Parameters are the internal numbers an AI model learns during training. A model’s size, such as “70 billion parameters”, counts them.
Also called weights, model weights, model size
In more detail
In a neural network, parameters (mostly weights) set how strongly each connection affects the next. Training adjusts them until the model’s outputs are good. Together they store everything the model has learned.
More parameters generally mean more capacity, but also more memory and computing power to run. Settings chosen before training, like learning speed, are hyperparameters, not parameters.
Related terms
Neural networkA neural network is an AI model made of layers of connected units, loosely inspired by the brain, that learns by adjusting the strength of its connections.HyperparameterA hyperparameter is a setting chosen before training an AI model, such as how fast it learns or how many layers it has, that shapes how training goes.Large language model (LLM)A large language model (LLM) is an AI model trained on vast amounts of text to understand and generate language. It powers chatbots like ChatGPT.Open-source AIOpen-source AI means models that are free to download, use and modify. Many are “open-weight”: the trained model is shared, but not the data it was trained on.QuantizationQuantization shrinks an AI model by storing its numbers with less precision, so it uses less memory and runs faster, with a small loss in quality.
Browse related tools
AI tools listed on BroUseAI in these categories.
