Matches in SemOpenAlex for { <https://semopenalex.org/work/W4375959555> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4375959555 abstract "Machine learning (ML) is successful in achieving human-level artificial intelligence in various fields. However, it lacks the ability to explain an outcome due to its black-box nature. While recent efforts on explainable AI (XAI) has received significant attention, most of the existing solutions are not applicable in real-time systems since they map interpretability as an optimization problem, which leads to numerous iterations of time-consuming complex computations. Although there are existing hardware-based acceleration framework for XAI, they are implemented through FPGA and designed for specific tasks, leading to expensive cost and lack of flexibility. In this paper, we propose a simple yet efficient framework to accelerate various XAI algorithms with existing hardware accelerators. Specifically, this paper makes three important contributions. (1) The proposed method is the first attempt in exploring the effectiveness of Tensor Processing Unit (TPU) to accelerate XAI. (2) Our proposed solution explores the close relationship between several existing XAI algorithms with matrix computations, and exploits the synergy between convolution and Fourier transform, which takes full advantage of TPU's inherent ability in accelerating matrix computations. (3) Our proposed approach can lead to real-time outcome interpretation. Extensive experimental evaluation demonstrates that proposed approach deployed on TPU can provide drastic improvement in interpretation time (39x on average) as well as energy efficiency (69x on average) compared to existing acceleration techniques." @default.
- W4375959555 created "2023-05-10" @default.
- W4375959555 creator A5006818844 @default.
- W4375959555 creator A5013876571 @default.
- W4375959555 date "2023-05-04" @default.
- W4375959555 modified "2023-09-28" @default.
- W4375959555 title "Hardware Acceleration of Explainable Artificial Intelligence" @default.
- W4375959555 doi "https://doi.org/10.48550/arxiv.2305.04887" @default.
- W4375959555 hasPublicationYear "2023" @default.
- W4375959555 type Work @default.
- W4375959555 citedByCount "0" @default.
- W4375959555 crossrefType "posted-content" @default.
- W4375959555 hasAuthorship W4375959555A5006818844 @default.
- W4375959555 hasAuthorship W4375959555A5013876571 @default.
- W4375959555 hasBestOaLocation W43759595551 @default.
- W4375959555 hasConcept C105795698 @default.
- W4375959555 hasConcept C113775141 @default.
- W4375959555 hasConcept C11413529 @default.
- W4375959555 hasConcept C117896860 @default.
- W4375959555 hasConcept C119857082 @default.
- W4375959555 hasConcept C121332964 @default.
- W4375959555 hasConcept C13164978 @default.
- W4375959555 hasConcept C149635348 @default.
- W4375959555 hasConcept C154945302 @default.
- W4375959555 hasConcept C199360897 @default.
- W4375959555 hasConcept C2780598303 @default.
- W4375959555 hasConcept C2781067378 @default.
- W4375959555 hasConcept C33923547 @default.
- W4375959555 hasConcept C41008148 @default.
- W4375959555 hasConcept C42935608 @default.
- W4375959555 hasConcept C45347329 @default.
- W4375959555 hasConcept C45374587 @default.
- W4375959555 hasConcept C50644808 @default.
- W4375959555 hasConcept C527412718 @default.
- W4375959555 hasConcept C74650414 @default.
- W4375959555 hasConceptScore W4375959555C105795698 @default.
- W4375959555 hasConceptScore W4375959555C113775141 @default.
- W4375959555 hasConceptScore W4375959555C11413529 @default.
- W4375959555 hasConceptScore W4375959555C117896860 @default.
- W4375959555 hasConceptScore W4375959555C119857082 @default.
- W4375959555 hasConceptScore W4375959555C121332964 @default.
- W4375959555 hasConceptScore W4375959555C13164978 @default.
- W4375959555 hasConceptScore W4375959555C149635348 @default.
- W4375959555 hasConceptScore W4375959555C154945302 @default.
- W4375959555 hasConceptScore W4375959555C199360897 @default.
- W4375959555 hasConceptScore W4375959555C2780598303 @default.
- W4375959555 hasConceptScore W4375959555C2781067378 @default.
- W4375959555 hasConceptScore W4375959555C33923547 @default.
- W4375959555 hasConceptScore W4375959555C41008148 @default.
- W4375959555 hasConceptScore W4375959555C42935608 @default.
- W4375959555 hasConceptScore W4375959555C45347329 @default.
- W4375959555 hasConceptScore W4375959555C45374587 @default.
- W4375959555 hasConceptScore W4375959555C50644808 @default.
- W4375959555 hasConceptScore W4375959555C527412718 @default.
- W4375959555 hasConceptScore W4375959555C74650414 @default.
- W4375959555 hasLocation W43759595551 @default.
- W4375959555 hasOpenAccess W4375959555 @default.
- W4375959555 hasPrimaryLocation W43759595551 @default.
- W4375959555 hasRelatedWork W2114257558 @default.
- W4375959555 hasRelatedWork W2966862483 @default.
- W4375959555 hasRelatedWork W2988282777 @default.
- W4375959555 hasRelatedWork W3012234327 @default.
- W4375959555 hasRelatedWork W4205364923 @default.
- W4375959555 hasRelatedWork W4206534706 @default.
- W4375959555 hasRelatedWork W4229079080 @default.
- W4375959555 hasRelatedWork W4280636456 @default.
- W4375959555 hasRelatedWork W4309228605 @default.
- W4375959555 hasRelatedWork W3116497574 @default.
- W4375959555 isParatext "false" @default.
- W4375959555 isRetracted "false" @default.
- W4375959555 workType "article" @default.