About: Knowledge distillation

Facets (new session)
Description
Metadata
Settings
- Rule:
- Inverse Functional Properties:
- "Same As":

About: Knowledge distillation Goto Sponge NotDistinct Permalink

An Entity of Type : owl:Thing, within Data Space : dbpedia.demo.openlinksw.com associated with source document(s)
QRcode icon

http://dbpedia.demo.openlinksw.com/describe/?url=http%3A%2F%2Fdbpedia.org%2Fresource%2FKnowledge_distillation

In machine learning, knowledge distillation is the process of transferring knowledge from a large model to a smaller one. While large models (such as very deep neural networks or ensembles of many models) have higher knowledge capacity than small models, this capacity might not be fully utilized. It can be computationally just as expensive to evaluate a model even if it utilizes little of its knowledge capacity. Knowledge distillation transfers knowledge from a large model to a smaller model without loss of validity. As smaller models are less expensive to evaluate, they can be deployed on less powerful hardware (such as a mobile device).

Attributes	Values
rdfs:label	Knowledge distillation (en)
rdfs:comment	In machine learning, knowledge distillation is the process of transferring knowledge from a large model to a smaller one. While large models (such as very deep neural networks or ensembles of many models) have higher knowledge capacity than small models, this capacity might not be fully utilized. It can be computationally just as expensive to evaluate a model even if it utilizes little of its knowledge capacity. Knowledge distillation transfers knowledge from a large model to a smaller model without loss of validity. As smaller models are less expensive to evaluate, they can be deployed on less powerful hardware (such as a mobile device). (en)
dcterms:subject	Machine learning Deep learning
Wikipage page ID	62295363 (xsd:integer)
Wikipage revision ID	1115390679 (xsd:integer)
Link from a Wikipage to another Wikipage	Ensemble averaging (machine learning) Natural language processing Neural network Deep neural network Pseudolikelihood Cross entropy Mean Geoffrey Hinton Gradient Mobile device Concision Logit Machine learning Statistical model Machine learning Learning rate Preprint Object detection Acoustic model Deep learning Softmax function Dataset Loss function Soft-in soft-out decoder Statistical model validation Statistical classification Image classification
Link from a Wikipage to an external page	https://ai.google/research/pubs/pub44873
sameAs	Knowledge distillation Knowledge distillation
dbp:wikiPageUsesTemplate	dbt:Short_description
has abstract	In machine learning, knowledge distillation is the process of transferring knowledge from a large model to a smaller one. While large models (such as very deep neural networks or ensembles of many models) have higher knowledge capacity than small models, this capacity might not be fully utilized. It can be computationally just as expensive to evaluate a model even if it utilizes little of its knowledge capacity. Knowledge distillation transfers knowledge from a large model to a smaller model without loss of validity. As smaller models are less expensive to evaluate, they can be deployed on less powerful hardware (such as a mobile device). Knowledge distillation has been successfully used in several applications of machine learning such as object detection, acoustic models, and natural language processing.Recently, it has also been introduced to graph neural networks applicable to non-grid data. (en)
prov:wasDerivedFrom	wikipedia-en:Knowledge_distillation?oldid=1115390679&ns=0
page length (characters) of wiki page	9603 (xsd:nonNegativeInteger)
foaf:isPrimaryTopicOf	wikipedia-en:Knowledge_distillation
is Link from a Wikipage to another Wikipage of	Deep learning speech synthesis GPT-2 Distillation (machine learning) Dark knowledge
is Wikipage redirect of	Distillation (machine learning) Dark knowledge
is foaf:primaryTopic of	wikipedia-en:Knowledge_distillation

Faceted Search & Find service v1.17_git139 as of Feb 29 2024

Alternative Linked Data Documents: ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 08.03.3330 as of Mar 19 2024, on Linux (x86_64-generic-linux-glibc212), Single-Server Edition (378 GB total memory, 59 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software