Concept information
Preferred term
stochastic gradient descent
Definition
- "A gradient descent algorithm in which the batch size is one. In other words, SGD trains on a single example chosen uniformly at random from a training set." (source: https://developers.google.com/machine-learning/glossary/).
Broader concept
Entry terms
- SGD
is implemented by
In other languages
-
French
-
algorithme de descente du gradient stochastique
-
algorithme du gradient stochastique
URI
http://data.loterre.fr/ark:/67375/LTK-DF6LPDQ5-M
{{label}}
{{#each values }} {{! loop through ConceptPropertyValue objects }}
{{#if prefLabel }}
{{/if}}
{{/each}}
{{#if notation }}{{ notation }} {{/if}}{{ prefLabel }}
{{#ifDifferentLabelLang lang }} ({{ lang }}){{/ifDifferentLabelLang}}
{{#if vocabName }}
{{ vocabName }}
{{/if}}