Gradient Descent
Updating weights in the direction that reduces the loss.
Visão geral
Gradient descent adjusts each weight by a small step opposite the gradient, repeating until the loss stops falling. It solves the problem of finding a good configuration in a space far too large to search. It exists as the simplest member of a family of optimisers, and the practical work is in choosing the step size, the batch size and the schedule rather than in the update rule itself.
Grafo de tecnologias
Como Gradient Descent se liga ao resto do stack.
Usa e depende de
- Learning Rate concept Algorithms Gradient Descent uses Learning Rate High ✓ source
Aplicado a
- Fine-tuning technique Techniques Gradient Descent used for Fine-tuning High ✓ source
- Pretraining technique Techniques Gradient Descent used for Pretraining High ✓ source