Matches in SemOpenAlex for { <https://semopenalex.org/work/W4323647529> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4323647529 endingPage "526" @default.
- W4323647529 startingPage "512" @default.
- W4323647529 abstract "Binary neural networks have recently begun to be used as a highly energy- and computation-efficient image processing technique for computer vision tasks. This paper proposes a novel extension of existing binary neural network technology based on the use of a Hadamard transform in the input layer of a binary neural network. Previous state-of-the-art binary neural networks require floating-point arithmetic at several parts of the neural network model computation in order to maintain a sufficient level of accuracy. The Hadamard transform is similar to a Discrete Cosine Transform (used in the popular JPEG image compression method) except that it does not include expensive multiplication operations. In this paper, it is shown that the Hadamard transform can be used to replace the most expensive floating-point arithmetic portion of a binary neural network. In order to test the efficacy of this proposed method, three types of experiments were conducted: application of the proposed method to several state-of-the-art neural network models, verification of its effectiveness in a large image dataset (ImageNet), and experiments to verify the effectiveness of the Hadamard transform by comparing the performance of binary neural networks with and without the Hadamard transform. The results show that the Hadamard transform can be used to implement a highly energy-efficient binary neural network with only a miniscule loss of accuracy." @default.
- W4323647529 created "2023-03-10" @default.
- W4323647529 creator A5022912434 @default.
- W4323647529 creator A5048785540 @default.
- W4323647529 date "2023-01-01" @default.
- W4323647529 modified "2023-09-24" @default.
- W4323647529 title "Energy-Efficient Image Processing Using Binary Neural Networks with Hadamard Transform" @default.
- W4323647529 cites W1983309378 @default.
- W4323647529 cites W1996550590 @default.
- W4323647529 cites W2007339694 @default.
- W4323647529 cites W2064382863 @default.
- W4323647529 cites W2107146360 @default.
- W4323647529 cites W2108598243 @default.
- W4323647529 cites W2134809980 @default.
- W4323647529 cites W2194775991 @default.
- W4323647529 cites W2300242332 @default.
- W4323647529 cites W2749307095 @default.
- W4323647529 cites W2887447938 @default.
- W4323647529 cites W3001433835 @default.
- W4323647529 cites W3008515144 @default.
- W4323647529 cites W3104151879 @default.
- W4323647529 cites W3130641740 @default.
- W4323647529 cites W3174892017 @default.
- W4323647529 cites W3176211720 @default.
- W4323647529 cites W4211206257 @default.
- W4323647529 cites W4226419870 @default.
- W4323647529 cites W4243830420 @default.
- W4323647529 doi "https://doi.org/10.1007/978-3-031-26348-4_30" @default.
- W4323647529 hasPublicationYear "2023" @default.
- W4323647529 type Work @default.
- W4323647529 citedByCount "0" @default.
- W4323647529 crossrefType "book-chapter" @default.
- W4323647529 hasAuthorship W4323647529A5022912434 @default.
- W4323647529 hasAuthorship W4323647529A5048785540 @default.
- W4323647529 hasConcept C11413529 @default.
- W4323647529 hasConcept C115961682 @default.
- W4323647529 hasConcept C134306372 @default.
- W4323647529 hasConcept C153180895 @default.
- W4323647529 hasConcept C154945302 @default.
- W4323647529 hasConcept C193828747 @default.
- W4323647529 hasConcept C2221639 @default.
- W4323647529 hasConcept C33923547 @default.
- W4323647529 hasConcept C41008148 @default.
- W4323647529 hasConcept C48372109 @default.
- W4323647529 hasConcept C50644808 @default.
- W4323647529 hasConcept C60292330 @default.
- W4323647529 hasConcept C9417928 @default.
- W4323647529 hasConcept C94375191 @default.
- W4323647529 hasConceptScore W4323647529C11413529 @default.
- W4323647529 hasConceptScore W4323647529C115961682 @default.
- W4323647529 hasConceptScore W4323647529C134306372 @default.
- W4323647529 hasConceptScore W4323647529C153180895 @default.
- W4323647529 hasConceptScore W4323647529C154945302 @default.
- W4323647529 hasConceptScore W4323647529C193828747 @default.
- W4323647529 hasConceptScore W4323647529C2221639 @default.
- W4323647529 hasConceptScore W4323647529C33923547 @default.
- W4323647529 hasConceptScore W4323647529C41008148 @default.
- W4323647529 hasConceptScore W4323647529C48372109 @default.
- W4323647529 hasConceptScore W4323647529C50644808 @default.
- W4323647529 hasConceptScore W4323647529C60292330 @default.
- W4323647529 hasConceptScore W4323647529C9417928 @default.
- W4323647529 hasConceptScore W4323647529C94375191 @default.
- W4323647529 hasLocation W43236475291 @default.
- W4323647529 hasOpenAccess W4323647529 @default.
- W4323647529 hasPrimaryLocation W43236475291 @default.
- W4323647529 hasRelatedWork W1482571704 @default.
- W4323647529 hasRelatedWork W1591194399 @default.
- W4323647529 hasRelatedWork W2104912729 @default.
- W4323647529 hasRelatedWork W2112842517 @default.
- W4323647529 hasRelatedWork W2136054869 @default.
- W4323647529 hasRelatedWork W2174508532 @default.
- W4323647529 hasRelatedWork W2343531879 @default.
- W4323647529 hasRelatedWork W2544864878 @default.
- W4323647529 hasRelatedWork W2738889589 @default.
- W4323647529 hasRelatedWork W4367598285 @default.
- W4323647529 isParatext "false" @default.
- W4323647529 isRetracted "false" @default.
- W4323647529 workType "book-chapter" @default.