📈

Gradient Descent

★★★☆☆High School

📖Definition

Gradient descent is an optimization algorithm that iteratively moves in the opposite direction of the gradient to find the minimum.

x_n+1 = xₙ - α ∇ f(xₙ)

Gradient descent update rule

Learning rate (step size)

예제 1

Apply gradient descent to f(x) = x² with x₀ = 4, α = 0.5.

Neural network training

Model parameter optimization

Regression analysis

#경사하강#기울기#gradient descent#optimization