Softmax Function: Activation for Classification
About this video
The softmax function, explained step by step.
The Softmax function transforms a neural network's output logits into a probability distribution that sums to 1. It is the standard activation for multi-class classification, from image classifiers to the vocabulary layer of language models like GPT.
Video transcript
- 0:01 Softmax takes the network's scores, applies the exponential to each one and
- 0:06 divides by the sum.
- 0:07 Out come probabilities that add up to 1:
- 0:10 cat gets 63 percent.
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.