In the process of training the neural network, our goal is to keep the loss function reduced. Which of the following methods do we usually use to minimize the loss function?

Question

Options

• AGradient descent
• BDropout
• CCross-validation
• DRegularization

• A
  79% (15)
• B
  11% (2)
• C
  5% (1)
• D
  5% (1)

Explanation

Gradient descent is the optimization algorithm used to minimize the loss function during neural network training - it computes the gradient of the loss with respect to the model's weights and iteratively updates those weights in the direction that reduces the loss. Dropout is a regularization technique that randomly deactivates neurons during training to prevent overfitting, but it does not minimize the loss function directly. Cross-validation is a model evaluation technique used to assess generalization performance across data splits, not an optimization method. Regularization (such as L1 or L2) adds a penalty term to the loss function to discourage overly complex models, but it modifies what is being minimized rather than performing the minimization itself. Memory tip: think "descent" as walking downhill - gradient descent finds the steepest downward slope on the loss surface and takes a step in that direction, which is exactly what minimizing a function means.

No community discussion yet for this question.