FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3037801075> ?p ?o ?g. }

• W3037801075 endingPage "625" @default.
• W3037801075 startingPage "612" @default.
• W3037801075 abstract "Approximate computing provides an emerging approach to design high performance and low power arithmetic circuits. The logarithmic multiplier (LM) converts multiplication into addition and has inherent approximate characteristics. In this article, dynamic range approximate LMs (DR-ALMs) for machine learning applications are proposed; they use Mitchell’s approximation and a dynamic range operand truncation scheme. The worst case (absolute and relative) errors for the proposed DR-ALMs are analyzed. The accuracy and the hardware overhead of these designs are provided to select the best approximate scheme according to different metrics. The proposed DR-ALMs are compared with the conventional LM with exact operands and previous approximate multipliers; the results show that the power-delay product (PDP) of the best proposed DR-ALM (DR-ALM-6) are decreased by up to 54.07 percent with the mean relative error distance (MRED) decreasing by 21.30 percent compared with 16-bit conventional design. Case studies for three machine learning applications show the viability of the proposed DR-ALMs. Compared with the exact multiplier and its conventional counterpart, the back-propagation classifier with DR-ALMs with a truncation length larger than 4 has a similar classification result for the three datasets; the K-means clustering application with all DR-ALMs has a similar clustering result for four datasets; and the handwritten digit recognition application with DR-ALM-5 or DR-ALM-6 for LeNet-5 achieves similar or even slightly higher recognition rate." @default.
• W3037801075 created "2020-07-02" @default.
• W3037801075 creator A5001979328 @default.
• W3037801075 creator A5010582173 @default.
• W3037801075 creator A5016864694 @default.
• W3037801075 creator A5023734605 @default.
• W3037801075 creator A5055800000 @default.
• W3037801075 creator A5063931122 @default.
• W3037801075 date "2021-10-01" @default.
• W3037801075 modified "2023-10-12" @default.
• W3037801075 title "Design and Analysis of Energy-Efficient Dynamic Range Approximate Logarithmic Multipliers for Machine Learning" @default.
• W3037801075 cites W1669276382 @default.
• W3037801075 cites W1910331302 @default.
• W3037801075 cites W1937403678 @default.
• W3037801075 cites W1979974858 @default.
• W3037801075 cites W1998824039 @default.
• W3037801075 cites W2017819499 @default.
• W3037801075 cites W2033224922 @default.
• W3037801075 cites W2034349555 @default.
• W3037801075 cites W2045294186 @default.
• W3037801075 cites W2065359960 @default.
• W3037801075 cites W2082279372 @default.
• W3037801075 cites W2090557012 @default.
• W3037801075 cites W2100344492 @default.
• W3037801075 cites W2102915015 @default.
• W3037801075 cites W2106484393 @default.
• W3037801075 cites W2111013824 @default.
• W3037801075 cites W2112796928 @default.
• W3037801075 cites W2121819644 @default.
• W3037801075 cites W2124651102 @default.
• W3037801075 cites W2135089667 @default.
• W3037801075 cites W2323130283 @default.
• W3037801075 cites W2461274627 @default.
• W3037801075 cites W2516350781 @default.
• W3037801075 cites W2517001613 @default.
• W3037801075 cites W2589986623 @default.
• W3037801075 cites W2742536119 @default.
• W3037801075 cites W2769672439 @default.
• W3037801075 cites W2790014825 @default.
• W3037801075 cites W2790285612 @default.
• W3037801075 cites W2807493440 @default.
• W3037801075 cites W2899084402 @default.
• W3037801075 cites W2900613774 @default.
• W3037801075 cites W2908518198 @default.
• W3037801075 cites W3009178428 @default.
• W3037801075 cites W4242921037 @default.
• W3037801075 doi "https://doi.org/10.1109/tsusc.2020.3004980" @default.
• W3037801075 hasPublicationYear "2021" @default.
• W3037801075 type Work @default.
• W3037801075 sameAs 3037801075 @default.
• W3037801075 citedByCount "22" @default.
• W3037801075 countsByYear W30378010752012 @default.
• W3037801075 countsByYear W30378010752021 @default.
• W3037801075 countsByYear W30378010752022 @default.
• W3037801075 countsByYear W30378010752023 @default.
• W3037801075 crossrefType "journal-article" @default.
• W3037801075 hasAuthorship W3037801075A5001979328 @default.
• W3037801075 hasAuthorship W3037801075A5010582173 @default.
• W3037801075 hasAuthorship W3037801075A5016864694 @default.
• W3037801075 hasAuthorship W3037801075A5023734605 @default.
• W3037801075 hasAuthorship W3037801075A5055800000 @default.
• W3037801075 hasAuthorship W3037801075A5063931122 @default.
• W3037801075 hasBestOaLocation W30378010751 @default.
• W3037801075 hasConcept C111919701 @default.
• W3037801075 hasConcept C11413529 @default.
• W3037801075 hasConcept C124584101 @default.
• W3037801075 hasConcept C134306372 @default.
• W3037801075 hasConcept C139719470 @default.
• W3037801075 hasConcept C154945302 @default.
• W3037801075 hasConcept C159985019 @default.
• W3037801075 hasConcept C162324750 @default.
• W3037801075 hasConcept C164620267 @default.
• W3037801075 hasConcept C192562407 @default.
• W3037801075 hasConcept C204323151 @default.
• W3037801075 hasConcept C2779960059 @default.
• W3037801075 hasConcept C33923547 @default.
• W3037801075 hasConcept C39927690 @default.
• W3037801075 hasConcept C41008148 @default.
• W3037801075 hasConcept C55526617 @default.
• W3037801075 hasConcept C73555534 @default.
• W3037801075 hasConcept C76155785 @default.
• W3037801075 hasConcept C82876162 @default.
• W3037801075 hasConcept C94375191 @default.
• W3037801075 hasConceptScore W3037801075C111919701 @default.
• W3037801075 hasConceptScore W3037801075C11413529 @default.
• W3037801075 hasConceptScore W3037801075C124584101 @default.
• W3037801075 hasConceptScore W3037801075C134306372 @default.
• W3037801075 hasConceptScore W3037801075C139719470 @default.
• W3037801075 hasConceptScore W3037801075C154945302 @default.
• W3037801075 hasConceptScore W3037801075C159985019 @default.
• W3037801075 hasConceptScore W3037801075C162324750 @default.
• W3037801075 hasConceptScore W3037801075C164620267 @default.
• W3037801075 hasConceptScore W3037801075C192562407 @default.
• W3037801075 hasConceptScore W3037801075C204323151 @default.
• W3037801075 hasConceptScore W3037801075C2779960059 @default.
• W3037801075 hasConceptScore W3037801075C33923547 @default.
• W3037801075 hasConceptScore W3037801075C39927690 @default.
• W3037801075 hasConceptScore W3037801075C41008148 @default.

• next