架构

Softmax

定义

A mathematical function that converts a vector of raw logits into a probability distribution summing to 1. Softmax is applied at the output of classifiers and language models to produce token probabilities used in sampling and decoding.

相关术语

Logit

The raw, unnormalised score produced by a model's final layer before the softmax function is applied. Logits are useful for calibration, temperature scaling, and understanding a model's confidence distribution across possible output classes.

Cross-Entropy Loss

The most common training objective for classification and language modelling tasks, measuring the difference between predicted probability distributions and true labels. Minimising cross-entropy loss during training drives the model to assign high probability to correct outputs.

Top-p Sampling (Nucleus Sampling)

A decoding strategy that restricts the model's next-token choices to the smallest set of tokens whose cumulative probability exceeds a threshold p. Used alongside temperature, top-p sampling balances output diversity and coherence in production LLM deployments.

了解术语只是第一步，将其落地应用才是第二步。

预约一次 Physical AI 适配性沟通，探讨这些 AI 概念如何转化到您所在的具体行业与业务挑战中。