← World of AI
Neural Networks
Gradient Descent
An optimisation method that updates parameters to reduce the model’s loss.
Gradient descent calculates how a small change in each model parameter would affect the loss. It then updates the parameters in the direction expected to reduce that loss.
The learning rate controls the size of each update. Variants such as stochastic gradient descent, momentum and adaptive optimisation improve speed, stability or performance on large datasets.
Also in Neural Networks
JOIN NOW
Begin the first module
It is free, it is the real curriculum, and if it is not for you, you have lost nothing but an evening.
Join any time · Build AI skills at your pace