MELMORAVaramis · AI Assistant
+ New chatMachine LearningHomeExploreMy CoursesVaramis AIExaminationProgress
Can you explain gradient descent?
Gradient descent
θ ← θ − α · ∇J(θ)
- • θ: model parameters
- • α: learning rate (step size)
- • ∇J(θ): gradient of the loss function
Explain with exampleVisualize on canvasQuiz me
What happens if the learning rate is too big?
If α is too large, each update overshoots the minimum, and the loss can bounce around or even diverge. A common fix is to start small and use a learning-rate schedule.
