FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3126716198> ?p ?o ?g. }

• W3126716198 abstract "Classifying sequential data as early and as accurately as possible is a challenging yet critical problem, especially when a sampling cost is high. One algorithm that achieves this goal is the sequential probability ratio test (SPRT), which is known as Bayes-optimal: it can keep the expected number of data samples as small as possible, given the desired error upper-bound. However, the original SPRT makes two critical assumptions that limit its application in real-world scenarios: (i) samples are independently and identically distributed, and (ii) the likelihood of the data being derived from each class can be calculated precisely. Here, we propose the SPRT-TANDEM, a deep neural network-based SPRT algorithm that overcomes the above two obstacles. The SPRT-TANDEM sequentially estimates the log-likelihood ratio of two alternative hypotheses by leveraging a novel Loss function for Log-Likelihood Ratio estimation (LLLR) while allowing correlations up to N(∈N) preceding samples. In tests on one original and two public video databases, Nosaic MNIST, UCF101, and SiW, the SPRT-TANDEM achieves statistically significantly better classification accuracy than other baseline classifiers, with a smaller number of data samples. The code and Nosaic MNIST are publicly available at https://github.com/TaikiMiyagawa/SPRT-TANDEM." @default.
• W3126716198 created "2021-02-15" @default.
• W3126716198 creator A5028205677 @default.
• W3126716198 creator A5031443710 @default.
• W3126716198 creator A5041006680 @default.
• W3126716198 creator A5071714722 @default.
• W3126716198 date "2021-05-03" @default.
• W3126716198 modified "2023-09-26" @default.
• W3126716198 title "Sequential Density Ratio Estimation for Simultaneous Optimization of Speed and Accuracy" @default.
• W3126716198 cites W1498436455 @default.
• W3126716198 cites W1504795361 @default.
• W3126716198 cites W1528566696 @default.
• W3126716198 cites W1546020435 @default.
• W3126716198 cites W1810943226 @default.
• W3126716198 cites W1965603950 @default.
• W3126716198 cites W1971976749 @default.
• W3126716198 cites W1989076763 @default.
• W3126716198 cites W2000725316 @default.
• W3126716198 cites W2008348094 @default.
• W3126716198 cites W2022367269 @default.
• W3126716198 cites W2027006437 @default.
• W3126716198 cites W2032610016 @default.
• W3126716198 cites W2035104901 @default.
• W3126716198 cites W2040322706 @default.
• W3126716198 cites W2045638068 @default.
• W3126716198 cites W2049877533 @default.
• W3126716198 cites W2050493487 @default.
• W3126716198 cites W2062291443 @default.
• W3126716198 cites W2095121438 @default.
• W3126716198 cites W2102689555 @default.
• W3126716198 cites W2106600012 @default.
• W3126716198 cites W2113263087 @default.
• W3126716198 cites W2123066336 @default.
• W3126716198 cites W2136414026 @default.
• W3126716198 cites W2136906168 @default.
• W3126716198 cites W2144095870 @default.
• W3126716198 cites W2145212427 @default.
• W3126716198 cites W2146502635 @default.
• W3126716198 cites W2151370270 @default.
• W3126716198 cites W2157285372 @default.
• W3126716198 cites W2161115820 @default.
• W3126716198 cites W2164011442 @default.
• W3126716198 cites W2164598857 @default.
• W3126716198 cites W2169134378 @default.
• W3126716198 cites W2170449627 @default.
• W3126716198 cites W2312052290 @default.
• W3126716198 cites W2524083015 @default.
• W3126716198 cites W2551393996 @default.
• W3126716198 cites W2744538883 @default.
• W3126716198 cites W2754051771 @default.
• W3126716198 cites W2771712594 @default.
• W3126716198 cites W2886189758 @default.
• W3126716198 cites W2904485375 @default.
• W3126716198 cites W2907108374 @default.
• W3126716198 cites W2945880513 @default.
• W3126716198 cites W2963524571 @default.
• W3126716198 cites W2963616706 @default.
• W3126716198 cites W2964121744 @default.
• W3126716198 cites W2964182247 @default.
• W3126716198 cites W2970971581 @default.
• W3126716198 cites W2972528402 @default.
• W3126716198 cites W3037059779 @default.
• W3126716198 cites W3099878876 @default.
• W3126716198 cites W3118438167 @default.
• W3126716198 cites W848133049 @default.
• W3126716198 cites W91088564 @default.
• W3126716198 hasPublicationYear "2021" @default.
• W3126716198 type Work @default.
• W3126716198 sameAs 3126716198 @default.
• W3126716198 citedByCount "1" @default.
• W3126716198 countsByYear W31267161982021 @default.
• W3126716198 crossrefType "proceedings-article" @default.
• W3126716198 hasAuthorship W3126716198A5028205677 @default.
• W3126716198 hasAuthorship W3126716198A5031443710 @default.
• W3126716198 hasAuthorship W3126716198A5041006680 @default.
• W3126716198 hasAuthorship W3126716198A5071714722 @default.
• W3126716198 hasConcept C105795698 @default.
• W3126716198 hasConcept C107673813 @default.
• W3126716198 hasConcept C111919701 @default.
• W3126716198 hasConcept C11413529 @default.
• W3126716198 hasConcept C122123141 @default.
• W3126716198 hasConcept C134306372 @default.
• W3126716198 hasConcept C14036430 @default.
• W3126716198 hasConcept C141513077 @default.
• W3126716198 hasConcept C151201525 @default.
• W3126716198 hasConcept C154945302 @default.
• W3126716198 hasConcept C190502265 @default.
• W3126716198 hasConcept C207201462 @default.
• W3126716198 hasConcept C33923547 @default.
• W3126716198 hasConcept C34602496 @default.
• W3126716198 hasConcept C41008148 @default.
• W3126716198 hasConcept C43126263 @default.
• W3126716198 hasConcept C50644808 @default.
• W3126716198 hasConcept C78458016 @default.
• W3126716198 hasConcept C86803240 @default.
• W3126716198 hasConceptScore W3126716198C105795698 @default.
• W3126716198 hasConceptScore W3126716198C107673813 @default.
• W3126716198 hasConceptScore W3126716198C111919701 @default.
• W3126716198 hasConceptScore W3126716198C11413529 @default.
• W3126716198 hasConceptScore W3126716198C122123141 @default.

• next