Learn Before
Concept

Output Layer of Softmax Regression

The output layer of softmax regression generates a probability distribution y^\hat{\mathbf{y}}, where each entry y^i\hat{y}_i represents the predicted probability that the input belongs to a particular class. These probabilities are calculated by applying the softmax activation function to the raw output scores o\mathbf{o}. To ensure the outputs represent valid probabilities, the operation exponentiates each score and normalizes it by the sum of all exponentiated scores:

y^i=exp(oi)jexp(oj)\hat{y}_i = \frac{\exp(o_i)}{\sum_j \exp(o_j)}

This transforms the unconstrained linear model outputs into a valid probability distribution.

0

2

Updated 2026-05-03

Tags

Data Science

Ch.1 Pre-training - Foundations of Large Language Models

Foundations of Large Language Models

Foundations of Large Language Models Course

Computing Sciences

D2L

Dive into Deep Learning @ D2L