Adam Optimizer
/ˈædəm/
An adaptive learning rate optimization algorithm combining momentum and RMSprop.
In italiano: Ottimizzatore AdamAdam (Adaptive Moment Estimation) computes adaptive learning rates for each parameter using first and second moment estimates. It's the default optimizer for many deep learning applications due to its robustness.
Examples
- Training transformers
- Deep neural networks
- Default optimizer in many frameworks