Simulation-Based Hardware Exploration for Shapley Value Calculations...24th International Conference of Informatics, Management and Technology in Healthcare (ICIMTH), July 3-5, 2026, Athens, Greece.
Shapley values are a popular method used to explain the output of machine learning models. They proved to be an important tool for providing trustworthy machine learning systems in healthcare. However, their exact computation is computationally expensive. Various approximation methods have been prop...
| Publicado en: | Studies in Health Technology & Informatics Vol. 338; pp. 524 - 529 |
|---|---|
| Autores principales: | , , |
| Formato: | equations & formulas proceedings tables/charts Journal Article |
| Publicado: |
Sage Publications Inc.
2026
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=195115674&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 195115674 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 09269630 U1V jtl: Studies in Health Technology & Informatics issn: 09269630 maglogo: N pubinfo: dt: 2026 vid: 338 pid: 344 pub: Sage Publications Inc. place: Thousand Oaks, California artinfo: ui: 195115674 195115674 195115674 10.3233/SHTI260899 195115674 ppf: 524 ppct: 5 formats: tig: atl: Simulation-Based Hardware Exploration for Shapley Value Calculations...24th International Conference of Informatics, Management and Technology in Healthcare (ICIMTH), July 3-5, 2026, Athens, Greece. aug: au: RUST, Johannes AUTEXIER, Serge DRECHSLER, Rolf affil: German Research Center for Artificial Intelligence, Bremen, Germany sug: subj: Simulations Machine Learning Congresses and Conferences Greece Greece Benchmarking ab: Shapley values are a popular method used to explain the output of machine learning models. They proved to be an important tool for providing trustworthy machine learning systems in healthcare. However, their exact computation is computationally expensive. Various approximation methods have been proposed, often implemented in high level programming languages such as Python. In this work, efficient computations of Shapley values on RISC-V based systems and specialized hardware are explored. Following recent trends of quantized neural networks, an implementation compatible with fixed point implementations is proposed. Using a virtual prototype, the different implementations of Shapley value calculations are benchmarked for different RISC-V ISA extensions and compared to a simulated hardware implementation for quantized Shapley values. pubtype: Academic Journal doctype: equations & formulas proceedings tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|