Distilling the Knowledge in a Neural Network
Work-level record. Its arXiv versions and any conference or journal version are listed as sources, each with its own date. A citation to the work does not identify which version the citing author read.
- Issued by
- No issuing record yet. A missing record is a gap in coverage.
- Authors credited
- Jeff Dean · Oriol Vinyals
- Dates
- Published 2015-03-09 authorship evidence authorship evidence
- Exact source
- Distilling the Knowledge in a Neural Network arXiv · published 2015-03-09 · arXiv abstract page, retrieved for the candidate pack on 2026-10-28 (SHA-256 d6218cf8fa05a50466fc6dcb0e3b4b59f188273027f6df10a55dbd8e0ddcd53b). Submission history as arXiv records it (UTC): v1 9 March 2015. The page serves the latest version; each version is a separate expression, and only the one a record names was read.
- Distilling the Knowledge in a Neural Network arXiv · published 2015-03-09 · arXiv:1503.02531v1, submitted 9 March 2015 (UTC). Retrieved for the candidate pack on 2026-10-28 (SHA-256 74e6689115c539db499f9d6153edecb364059926fd45402454f8210442444c5a). The author list is the byline as printed on the first page.
Appears in
No collection holds a record about this document yet.
Versions
No other versions of this document are recorded. The evidence applies to the source version listed above. Other versions, such as a preprint, working paper or journal publication, are not identified or substituted.
Issue and authorship records
- Author: Jeff DeanJeff Dean is a credited author of Distilling the Knowledge in a Neural Network.2015-03-09 · publication · Stated in source · Supported Inspect claim & evidence ↗Jeff Dean: person page →
- Author: Oriol VinyalsOriol Vinyals is a credited author of Distilling the Knowledge in a Neural Network.2015-03-09 · publication · Stated in source · Supported Inspect claim & evidence ↗Oriol Vinyals: person page →
Documentary relations
Each relation is listed separately. Citing, crediting and reporting the use of a method are different acts, and none of them shows agreement or influence by itself.
Cited by · 1
Recorded documents that explicitly reference this one. A citation to a work does not identify which version was read.
- Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak SupervisionWeak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision cites Distilling the Knowledge in a Neural Network.2023-12-14 · publication · Stated in source · Supported Inspect claim & evidence ↗Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision: document page →
Not recorded for this document: cites · explicitly credits · reports using a method from · method reported as used by · applies parts of · parts applied by · discusses · reports evaluation of. A missing record does not show that the relation does not exist.
What the document says it adds
The document’s own description of its contribution, quoted from the version each row names. A claim to be the first is the document’s claim; Selekoa does not assess it.
- In its own wordsThe authors state that they extend earlier work by Caruana and collaborators on compressing an ensemble's knowledge into a single model, using a different compression technique.“Caruana and his collaborators [1] have shown that it is possible to compress the knowledge in an ensemble into a single model which is much easier to deploy and we develop this approach further using a different compression technique.” arXiv v1, PDF p. 1, abstract2015-03-09 · publication · Stated in source · Supported Inspect claim & evidence ↗
- In its own wordsThe paper also introduces an ensemble of full models and specialist models that learn to distinguish fine-grained classes the full models confuse.“We also introduce a new type of ensemble composed of one or more full models and many specialist models which learn to distinguish fine-grained classes that the full models confuse.” arXiv v1, PDF p. 1, abstract2015-03-09 · publication · Stated in source · Supported Inspect claim & evidence ↗