Gradient Descent
About this video
Gradient descent, step by step: how the slope guides each weight update.
Gradient descent is the algorithm that trains almost every neural network. It computes the slope of the loss function with respect to each weight and takes a small step in the opposite direction, controlled by the learning rate, until it reaches a minimum where the error stops falling and the model has converged.
Video transcript
- 0:01 Gradient descent measures the slope of the loss and steps the other way.
- 0:05 Step by step, the weight walks down to the minimum.
More videos
Explainer
The Computational Graph and Automatic Differentiation
The computational graph and automatic differentiation, in action.
Explainer
Backpropagation: The Step-by-Step Derivation
The backpropagation derivation, factor by factor with the chain rule.
Explainer
Backpropagation: The Intuition
The intuition of backpropagation: the error flows backward through the network.
Explainer
Batch, Stochastic and Mini-Batch Gradient Descent
Batch, stochastic and mini-batch: three ways to traverse the data.