Concept information
Preferred term
generalization ability
Definition
- A measure of how accurately the algorithm is able to predict outputs from previously unknown data. (Qi et al., Applying Neural-Network-Based Machine Learning to Additive Manufacturing: Current Applications, Challenges, and Future Perspectives, in Engineering, 2019)
Broader concept
Note
- A model that can generalize is the opposite of a model that is overfitting. (Google for Developers - Machine Learning Glossary)
- Generalization ability can be evaluated using the bias and variance measurements. (Zaras et al., Neural networks and backpropagation, in Deep Learning for Robot Perception and Cognition, 2022)
In other languages
-
French
URI
http://data.loterre.fr/ark:/67375/8LP-K2272WCM-6
{{label}}
{{#each values }} {{! loop through ConceptPropertyValue objects }}
{{#if prefLabel }}
{{/if}}
{{/each}}
{{#if notation }}{{ notation }} {{/if}}{{ prefLabel }}
{{#ifDifferentLabelLang lang }} ({{ lang }}){{/ifDifferentLabelLang}}
{{#if vocabName }}
{{ vocabName }}
{{/if}}