What term describes the settings that determine how the learning algorithm processes data to populate the model?

• A. Hyperparameters
• B. Model training parameters
• C. Epochs
• D. Confusion matrix

Answer: (A)

Hyperparameters are the settings that determine how the learning algorithm processes data to populate the model. They are configured before training and control aspects such as learning rate, network depth or number of layers, batch size, regularization strength, and the optimizer choice. These settings shape the learning dynamics, influencing how quickly and how well the model learns from the data. They are not learned from the data itself; the actual parameters the model ends up with (weights and biases) are learned during training. An epoch, in contrast, is simply one full pass through the training dataset, which is about iteration count rather than configuration. A confusion matrix is an evaluation tool used after training to assess performance, not a training configuration. Therefore, the term that best describes the settings guiding how the algorithm processes data to build the model is hyperparameters.