You are performing gradient descent with a learning rate () of 0.1 on a convex loss function. In the first iteration, the gradient is -3. What is the parameter update in this iteration?
Hint: Check the formula for from theory.
You are performing gradient descent with a learning rate () of 0.1 on a convex loss function. In the first iteration, the gradient is -3. What is the parameter update in this iteration?
Hint: Check the formula for from theory.
Create a free account to access the full topic