Parameter

In the context of machine learning, a parameter is a configuration variable that is internal to the model and whose value can be estimated or learned directly from the training data. These parameters define the model's mapping from input data to output predictions and are the essence of what the model "learns" during the training process. For instance, in a linear regression model, the parameters would be the slope and intercept, while in a neural network, they are the weights and biases associated with each connection and neuron.