How are model parameters optimized during training?Review LaterThey are set manually by the user.They are chosen through a search process.They are adjusted to minimize the discrepancy between model predictions and target values.They are fixed and do not change during training.

Model parameters are optimized during training through a process called gradient descent. Here's a step-by-step explanation:

1. Initialize Parameters: The process begins with the initialization of model parameters. These can be initialized randomly or by following a specific method.

2. Calculate Loss: The model then makes predictions using the current parameters and a loss function is used to measure the discrepancy between the model's predictions and the actual target values. This loss gives an idea of how well the model is performing.

3. Compute Gradient: The gradient of the loss function with respect to the model parameters is then computed. This gradient points in the direction of steepest ascent in the loss function.

4. Update Parameters: The model parameters are then updated by taking a step in the direction of steepest descent (opposite to the gradient). The size of the step is determined by the learning rate, a hyperparameter that controls how much the parameters should change in each update.

5. Repeat: Steps 2-4 are repeated until the loss function is minimized, or until a certain number of iterations have been reached.

This process allows the model to learn from the data by iteratively adjusting its parameters to minimize the discrepancy between its predictions and the actual target values.