Which term refers to the set of parameters that the algorithm learns from data during training?

Which term refers to the set of parameters that the algorithm learns from data during training?

• A. Model training parameters
• B. Epochs
• C. Underfitting
• D. Overfitting

Answer: (A)

The set of values that the model adjusts during training are the model's parameters—usually the weights and biases that define how inputs are transformed into outputs. These are the learnable, trainable quantities updated by the optimization process to minimize the error on the training data. Among the options, the phrase that best captures this idea is the one referring to the model's parameters learned through training. The other terms describe different concepts: epochs are the number of times the entire training dataset is processed; underfitting describes a too-simple model that fails to capture patterns; overfitting describes a model that fits training data too closely and struggles to generalize to new data.

The set of values that the model adjusts during training are the model's parameters—usually the weights and biases that define how inputs are transformed into outputs. These are the learnable, trainable quantities updated by the optimization process to minimize the error on the training data. Among the options, the phrase that best captures this idea is the one referring to the model's parameters learned through training. The other terms describe different concepts: epochs are the number of times the entire training dataset is processed; underfitting describes a too-simple model that fails to capture patterns; overfitting describes a model that fits training data too closely and struggles to generalize to new data.