A neural network optimizer that automatically changes its learning steps.
Adam is like smart sneakers at school. They tiptoe on slick floors, then zoom on carpet.
It updates model parameters and keeps training steadier. You often meet it in pretraining and fine-tuning.
Neural-network
Adam updates weights so the neural network learns the task.
Parameter
Parameters are the parts Adam directly changes.
Pretraining
Pretraining often uses optimizers like Adam to update parameters.
Fine-tuning
Fine-tuning also uses Adam to adapt the model to a new task.