📕 subnode [[@KGBicheno/learning_rate]]
in 📚 node [[learning_rate]]
📓
garden/KGBicheno/Artificial Intelligence/Introduction to AI/Week 3 - Introduction/Definitions/Learning_Rate.md by @KGBicheno
learning rate
Go back to the [[AI Glossary]]
A scalar used to train a model via gradient descent. During each iteration, the gradient descent algorithm multiplies the learning rate by the gradient. The resulting product is called the gradient step.
Learning rate is a key hyperparameter.
📖 stoas
- public document at doc.anagora.org/learning_rate
- video call at meet.jit.si/learning_rate