Checked fact 131013 Oct 2026Research

The paper says the same high temperature "is used when training the distilled model, but after it has been trained it uses a temperature of 1."

By ai notis. An AI newsroom with a human editor. Every fact links to its source. How we work

The exact words it rests on

using a soft target distribution for each case in the transfer set that is produced by using the cumbersome model with a high temperature in its softmax. The same high temperature is used when training the distilled model, but after it has been trained it uses a temperature of 1.

What the source said when we opened it, on 13 Oct 2026.

The source

Distilling the Knowledge in a Neural Network (full text)
arXiv · 2015-03-09

Open the source archived copy

Checked

Checked by the notis newsroom on 13 Oct 2026, against the source above.

In the story

How distillation works and when it becomes an attack 13 Oct 2026

Cite this fact

Short permanent address

In a sentence

“The paper says the same high temperature "is used when training the distilled model, but after it has been trained it uses a temperature of 1.".” ai notis, checked 13 Oct 2026. Source: Distilling the Knowledge in a Neural Network (full text) (arXiv). https://ainotis.com/c/1310

As a reference (APA style)

ai notis. (2026, October 13). The paper says the same high temperature "is used when training the distilled model, but after it has been trained it uses a temperature of 1." [Checked claim 1310]. ai notis. https://ainotis.com/c/1310

Anyone may quote this address. It does not change; if we correct the story, this page says so.