Double descent
id:
double-descent-166-7373980
title:
Double descent
text:
In statistics and machine learning, double descent is the phenomenon where a statistical model with a small number of parameters and a model with an extremely large number of parameters have a small test error, but a model whose number of parameters is about the same as the number of data points used to train the model will have a large error. This phenomenon has been considered surprising, as it contradicts assumptions about overfitting in classical machine learning.
brand slug:
wiki
category slug:
encyclopedia
description:
Concept in machine learning
original url:
https://en.wikipedia.org/wiki/Double_descent
date created:
2005-11-27T20:12:24Z
date modified:
2024-08-29T20:38:44Z
main entity:
{"identifier":"Q113511451","url":"https://www.wikidata.org/entity/Q113511451"}
image:
{"content_url":"https://upload.wikimedia.org/wikipedia/commons/d/d7/Double_descent_in_a_two-layer_neural_network_%28Figure_3a_from_Rocks_et_al._2022%29.png","width":3302,"height":1530}
fields total:
13
integrity:
16