A simple predictive model is defined by the function output = (weight_1 * input_1) + (weight_2 * input_2) + bias. During the training process, the model adjusts its internal values to better predict the output based on the inputs. Which components of this function represent the model's tunable parameters (collectively denoted as θ)?

Effect of Training on Model Parameters

Definition of Student's Probability Distribution ($P_\theta^s$)

Analysis of Model Specialization