Matches in SemOpenAlex for { <https://semopenalex.org/work/W2235151955> ?p ?o ?g. }
- W2235151955 endingPage "29" @default.
- W2235151955 startingPage "1" @default.
- W2235151955 abstract "Most state-of-the-art machine-learning (ML) algorithms do not consider the computational constraints of implementing the learned model on embedded devices. These constraints are, for example, the limited depth of the arithmetic unit, the memory availability, or the battery capacity. We propose a new learning framework, the Algorithmic Risk Minimization (ARM), which relies on Algorithmic-Stability, and includes these constraints inside the learning process itself. ARM allows one to train advanced resource-sparing ML models and to efficiently deploy them on smart embedded systems. Finally, we show the advantages of our proposal on a smartphone-based Human Activity Recognition application by comparing it to a conventional ML approach." @default.
- W2235151955 created "2016-06-24" @default.
- W2235151955 creator A5036611143 @default.
- W2235151955 creator A5045802198 @default.
- W2235151955 creator A5072692847 @default.
- W2235151955 date "2016-01-29" @default.
- W2235151955 modified "2023-09-26" @default.
- W2235151955 title "Learning Hardware-Friendly Classifiers Through Algorithmic Stability" @default.
- W2235151955 cites W1484946637 @default.
- W2235151955 cites W1510073064 @default.
- W2235151955 cites W1512208174 @default.
- W2235151955 cites W1538170657 @default.
- W2235151955 cites W1540155273 @default.
- W2235151955 cites W1564947197 @default.
- W2235151955 cites W1578255497 @default.
- W2235151955 cites W1976168687 @default.
- W2235151955 cites W1976354615 @default.
- W2235151955 cites W1995691260 @default.
- W2235151955 cites W2002243214 @default.
- W2235151955 cites W2006151125 @default.
- W2235151955 cites W2014158063 @default.
- W2235151955 cites W2022383670 @default.
- W2235151955 cites W2033559768 @default.
- W2235151955 cites W2034365297 @default.
- W2235151955 cites W2040884411 @default.
- W2235151955 cites W2053186076 @default.
- W2235151955 cites W2053586955 @default.
- W2235151955 cites W205974262 @default.
- W2235151955 cites W2068558570 @default.
- W2235151955 cites W2073002077 @default.
- W2235151955 cites W2077366952 @default.
- W2235151955 cites W2082233060 @default.
- W2235151955 cites W2084147663 @default.
- W2235151955 cites W2086729636 @default.
- W2235151955 cites W2087258353 @default.
- W2235151955 cites W2089880431 @default.
- W2235151955 cites W2092095117 @default.
- W2235151955 cites W2097308346 @default.
- W2235151955 cites W2100605071 @default.
- W2235151955 cites W2104226279 @default.
- W2235151955 cites W2105015905 @default.
- W2235151955 cites W2106491486 @default.
- W2235151955 cites W2108810117 @default.
- W2235151955 cites W2109445534 @default.
- W2235151955 cites W2112114220 @default.
- W2235151955 cites W2112738128 @default.
- W2235151955 cites W2118195127 @default.
- W2235151955 cites W2119335939 @default.
- W2235151955 cites W2122825543 @default.
- W2235151955 cites W2127091535 @default.
- W2235151955 cites W2130526756 @default.
- W2235151955 cites W2133078477 @default.
- W2235151955 cites W2139338362 @default.
- W2235151955 cites W2140550177 @default.
- W2235151955 cites W2149298154 @default.
- W2235151955 cites W2151462928 @default.
- W2235151955 cites W2151999543 @default.
- W2235151955 cites W2153861700 @default.
- W2235151955 cites W2157532876 @default.
- W2235151955 cites W2162341153 @default.
- W2235151955 cites W2505968561 @default.
- W2235151955 cites W2562162676 @default.
- W2235151955 cites W2997754947 @default.
- W2235151955 cites W2998993395 @default.
- W2235151955 cites W3000680563 @default.
- W2235151955 cites W3001645704 @default.
- W2235151955 cites W3022552533 @default.
- W2235151955 cites W3100743579 @default.
- W2235151955 cites W4233413206 @default.
- W2235151955 cites W4247675360 @default.
- W2235151955 cites W4253654031 @default.
- W2235151955 doi "https://doi.org/10.1145/2836165" @default.
- W2235151955 hasPublicationYear "2016" @default.
- W2235151955 type Work @default.
- W2235151955 sameAs 2235151955 @default.
- W2235151955 citedByCount "1" @default.
- W2235151955 countsByYear W22351519552020 @default.
- W2235151955 crossrefType "journal-article" @default.
- W2235151955 hasAuthorship W2235151955A5036611143 @default.
- W2235151955 hasAuthorship W2235151955A5045802198 @default.
- W2235151955 hasAuthorship W2235151955A5072692847 @default.
- W2235151955 hasConcept C111919701 @default.
- W2235151955 hasConcept C112972136 @default.
- W2235151955 hasConcept C113775141 @default.
- W2235151955 hasConcept C11413529 @default.
- W2235151955 hasConcept C119857082 @default.
- W2235151955 hasConcept C147764199 @default.
- W2235151955 hasConcept C149635348 @default.
- W2235151955 hasConcept C154945302 @default.
- W2235151955 hasConcept C162324750 @default.
- W2235151955 hasConcept C187736073 @default.
- W2235151955 hasConcept C199360897 @default.
- W2235151955 hasConcept C2780451532 @default.
- W2235151955 hasConcept C41008148 @default.
- W2235151955 hasConcept C48103436 @default.
- W2235151955 hasConcept C98045186 @default.
- W2235151955 hasConceptScore W2235151955C111919701 @default.
- W2235151955 hasConceptScore W2235151955C112972136 @default.