Matches in SemOpenAlex for { <https://semopenalex.org/work/W4324322828> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4324322828 abstract "In typical artificial neural networks, neurons adjust according to global calculations of a central processor, but in the brain neurons and synapses self-adjust based on local information. A man-made self-adjusting (distributed) system capable of performing machine-learning problems would have substantial scaling advantages over typical computational neural networks, in power consumption, speed, and robustness to damage. Furthermore, such a system would allow us to study physical learning without the added complexity of biology. Here we unveil the second-generation design of such a system – a transistor-based self-adjusting analog network that trains itself to perform a wide variety of tasks. Here we demonstrate basic features of the system, including the ability to monitor all internal states. This platform is already faster than a simulation of itself, and is thus an exciting platform for the investigation of physical learning." @default.
- W4324322828 created "2023-03-16" @default.
- W4324322828 creator A5037814935 @default.
- W4324322828 creator A5038956187 @default.
- W4324322828 creator A5052862439 @default.
- W4324322828 creator A5062389287 @default.
- W4324322828 creator A5064950398 @default.
- W4324322828 creator A5067400866 @default.
- W4324322828 date "2023-03-15" @default.
- W4324322828 modified "2023-09-26" @default.
- W4324322828 title "Circuits that train themselves: decentralized, physics-driven learning" @default.
- W4324322828 cites W1987048169 @default.
- W4324322828 cites W2527798464 @default.
- W4324322828 cites W2610274734 @default.
- W4324322828 cites W2807750997 @default.
- W4324322828 cites W2922440652 @default.
- W4324322828 cites W2942478991 @default.
- W4324322828 cites W2963206832 @default.
- W4324322828 cites W3003821665 @default.
- W4324322828 cites W3046016807 @default.
- W4324322828 cites W3191589221 @default.
- W4324322828 cites W4210678178 @default.
- W4324322828 cites W4223626430 @default.
- W4324322828 cites W4280500203 @default.
- W4324322828 doi "https://doi.org/10.1117/12.2648618" @default.
- W4324322828 hasPublicationYear "2023" @default.
- W4324322828 type Work @default.
- W4324322828 citedByCount "0" @default.
- W4324322828 crossrefType "proceedings-article" @default.
- W4324322828 hasAuthorship W4324322828A5037814935 @default.
- W4324322828 hasAuthorship W4324322828A5038956187 @default.
- W4324322828 hasAuthorship W4324322828A5052862439 @default.
- W4324322828 hasAuthorship W4324322828A5062389287 @default.
- W4324322828 hasAuthorship W4324322828A5064950398 @default.
- W4324322828 hasAuthorship W4324322828A5067400866 @default.
- W4324322828 hasConcept C119599485 @default.
- W4324322828 hasConcept C120314980 @default.
- W4324322828 hasConcept C127413603 @default.
- W4324322828 hasConcept C134146338 @default.
- W4324322828 hasConcept C41008148 @default.
- W4324322828 hasConceptScore W4324322828C119599485 @default.
- W4324322828 hasConceptScore W4324322828C120314980 @default.
- W4324322828 hasConceptScore W4324322828C127413603 @default.
- W4324322828 hasConceptScore W4324322828C134146338 @default.
- W4324322828 hasConceptScore W4324322828C41008148 @default.
- W4324322828 hasLocation W43243228281 @default.
- W4324322828 hasOpenAccess W4324322828 @default.
- W4324322828 hasPrimaryLocation W43243228281 @default.
- W4324322828 hasRelatedWork W1485627940 @default.
- W4324322828 hasRelatedWork W1596201972 @default.
- W4324322828 hasRelatedWork W1598943142 @default.
- W4324322828 hasRelatedWork W1986253068 @default.
- W4324322828 hasRelatedWork W2160425906 @default.
- W4324322828 hasRelatedWork W2348852432 @default.
- W4324322828 hasRelatedWork W2351378856 @default.
- W4324322828 hasRelatedWork W2385146268 @default.
- W4324322828 hasRelatedWork W2899486387 @default.
- W4324322828 hasRelatedWork W4313054100 @default.
- W4324322828 isParatext "false" @default.
- W4324322828 isRetracted "false" @default.
- W4324322828 workType "article" @default.