Concept information
Terme préférentiel
Boltzmann machine
Définition
- An RNN architecture with one or more hidden layers, an input or visible layer, and no output layer, that can learn probabilistic distributions on an input dataset and performs classification, regression, and feature learning operations. It is used as a pretraining model in applications that need preliminary data, such as computer vision and image classification. (Adapted from Oğuz et al., Introduction to deep learning and diagnosis in medicine, in Diagnostic Biomedical Signal and Image Processing Applications with Deep Learning Methods, 2023)
Concept générique
Concepts spécifiques
Synonyme(s)
- BM
Traductions
-
français
-
BM
URI
http://data.loterre.fr/ark:/67375/8LP-J98H6JZW-3
{{label}}
{{#each values }} {{! loop through ConceptPropertyValue objects }}
{{#if prefLabel }}
{{/if}}
{{/each}}
{{#if notation }}{{ notation }} {{/if}}{{ prefLabel }}
{{#ifDifferentLabelLang lang }} ({{ lang }}){{/ifDifferentLabelLang}}
{{#if vocabName }}
{{ vocabName }}
{{/if}}