Concept

Probability Distribution Output of an Encoder-Classifier Model

The output of a classification model, mathematically represented as Classifyω(Encodeθ^(x))\mathrm{Classify}_{\omega}(\mathrm{Encode}_{\hat{\theta}}(\mathbf{x})) for an input x\mathbf{x}, is a probability distribution over a predefined set of labels (e.g., {positive,negative,neutral}\{\mathrm{positive}, \mathrm{negative}, \mathrm{neutral}\}). This conditional distribution is denoted by Prω,θ^(x)\mathrm{Pr}_{\omega,\hat{\theta}}(\cdot|\mathbf{x}). To determine the final classification, the model selects the label associated with the highest probability in this calculated distribution.

0

1

Updated 2026-04-14

Contributors are:

Who are from:

Tags

Foundations of Large Language Models

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

Foundations of Large Language Models Course

Computing Sciences