{"id":71,"date":"2021-10-13T15:11:20","date_gmt":"2021-10-13T13:11:20","guid":{"rendered":"https:\/\/project.inria.fr\/leanai\/?page_id=71"},"modified":"2024-11-18T10:06:12","modified_gmt":"2024-11-18T09:06:12","slug":"publications","status":"publish","type":"page","link":"https:\/\/project.inria.fr\/leanai\/publications\/","title":{"rendered":"Publications"},"content":{"rendered":"\n<h2 class=\"wp-block-heading\">2021<\/h2>\n\n\n\n<ul class=\"wp-block-list\"><li>Mariko Tatsumi, Yuxiang Xie, Caroline White, Silviu-Ioan Filip, Olivier Sentieys, et al. MPTorch and MPArchimedes: Open Source Frameworks to Explore Custom Mixed-Precision Operations for DNN Training on Edge Devices. <em>ROAD4NN 2021 &#8211; 2nd ROAD4NN Workshop: Research Open Automatic Design for Neural Networks<\/em>, Dec 2021, San Francisco, United States. <a href=\"https:\/\/hal.inria.fr\/hal-03494256\">https:\/\/hal.inria.fr\/hal-03494256<\/a><\/li><\/ul>\n\n\n\n<h2 class=\"wp-block-heading\">2022<\/h2>\n\n\n\n<ul class=\"wp-block-list\"><li>Etienne Dupuis, Silviu-Ioan Filip, Olivier Sentieys, David Novo, Ian O&#8217;Connor, et al.. Approximations in Deep Learning. <em>Approximate Computing Techniques &#8211; From Component to Application Level<\/em>, pp.467-512, 2022, Springer. <a href=\"https:\/\/hal.inria.fr\/hal-03494874v1\">https:\/\/hal.inria.fr\/hal-03494874v1<\/a><\/li><li>Tobias Habermann, Jonas K\u00fchle, Martin Kumm, Anastasia Volkova. Hardware-Aware Quantization for Multiplierless Neural Network Controllers. <em>The IEEE Asia Pacific Conference on Circuits and Systems (APCCAS)<\/em>, Nov 2022, Shenzhen, China. <a href=\"https:\/\/hal.science\/hal-03827660\/\">https:\/\/hal.science\/hal-03827660<\/a><\/li><li>Mariko Tatsumi, Silviu-Ioan Filip, Caroline White, Olivier Sentieys, Guy Lemieux. Mixing Low-Precision Formats in Multiply-Accumulate Units for DNN Training, In <em>2022 International Conference on Field-Programmable Technology (ICFPT)<\/em>, Dec 2022, Hong Kong SAR, China. <a href=\"https:\/\/hal.inria.fr\/hal-03885471\/\">https:\/\/hal.inria.fr\/hal-03885471<\/a><\/li><\/ul>\n\n\n\n<h2 class=\"wp-block-heading\">2023<\/h2>\n\n\n\n<ul class=\"wp-block-list\"><li>Prachi Kashikar, Olivier Sentieys, Sharad Sinha. Lossless Neural Network Model Compression Through Exponent Sharing. In <em>IEEE Transactions on Very Large Scale (VLSI) Systems, vol. 31, no. 11, pp. 1816-1825<\/em>, 2023.<\/li><\/ul>\n\n\n\n<ul class=\"wp-block-list\"><li>R\u00e9mi Garcia, Anastasia Volkova. Toward the Multiple Constant Multiplication at Minimal Hardware Cost,&#8221; in <em>IEEE Transactions on Circuits and Systems I: Regular Papers, vol. 70, no. 5, pp. 1976-1988, May 2023<\/em>, doi: 10.1109\/TCSI.2023.3241859.&nbsp;<a href=\"https:\/\/hal.science\/hal-03784625\">https:\/\/hal.science\/hal-03784625<\/a><\/li><\/ul>\n\n\n\n<ul class=\"wp-block-list\"><li>Debasmita Lohar, Clothilde Jeangoudoux, Anastasia Volkova, Eva Darulova. <em>Sound Mixed Fixed-Point Quantization of Neural Networks. ACM Trans. Embed. Comput. Syst. 22, Article 136 (October 2023), 26 pages<\/em>.&nbsp;<a href=\"https:\/\/doi.org\/10.1145\/3609118\">https:\/\/doi.org\/10.1145\/3609118<\/a><\/li><\/ul>\n\n\n\n<ul class=\"wp-block-list\"><li>C\u00e9dric Gernigon, Silviu-Ioan Filip, Olivier Sentieys, Cl\u00e9ment Coggiola, Mickael Bruno. Low-Precision Floating-Point for Efficient On-Board Deep Neural Network Processing. In <em>2023 European Data Handling &amp; Data Processing (EDHPC)<\/em>, Oct 2023, Juan-Les-Pins, France. <a href=\"https:\/\/hal.science\/hal-04252197\/\">https:\/\/hal.science\/hal-04252197<\/a><\/li><li>Van-Phu Ha, Olivier Sentieys. Maximizing Computing Accuracy on Resource-Constrained Architectures. In <em>2023 IEEE\/ACM Design, Automation and Test in Europe (DATE)<\/em>, Apr 2023, Antwerp, Belgium. <a href=\"https:\/\/inria.hal.science\/hal-03885240\/\">https:\/\/inria.hal.science\/hal-03885240<\/a><\/li><li>Nicolas Brisebarre, Silviu-Ioan Filip. Towards Machine-Efficient Rational <code>\\(L^\\infty\\)<\/code>-Approximations of Mathematical Functions. In <em>2023 IEEE Symposium on Computer Arithmetic (ARITH)<\/em>, Sep 2023, Portland, USA. Winner of the best paper award at the conference. <a href=\"https:\/\/hal.science\/hal-04093020\/\">https:\/\/hal.science\/hal-04093020<\/a><\/li><\/ul>\n\n\n\n<h2 class=\"wp-block-heading\">2024<\/h2>\n\n\n\n<ul class=\"wp-block-list\"><li>Sami Ben Ali, Silviu-Ioan Filip, Olivier Sentieys. A Stochastic Rounding-Enabled Low-Precision Floating-Point MAC for DNN Training. In <em>2024 IEEE\/ACM Design, Automation and Test in Europe (DATE)<\/em>, Mar 2024, Valencia, Spain. <a href=\"https:\/\/hal.science\/hal-04380270\">https:\/\/hal.science\/hal-04380270<\/a><\/li><\/ul>\n\n\n\n<ul class=\"wp-block-list\"><li>C\u00e9dric Gernigon, Silviu-Ioan Filip, Olivier Sentieys, Cl\u00e9ment Coggiola, Micka\u00ebl Bruno. AdaQAT: Adaptive Bit-Width Quantization-Aware Training, <em>in proceeding of the 6th IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS)<\/em>, Apr 2024, Abu Dhabi, UAE. <a href=\"https:\/\/hal.science\/hal-04549245\" data-type=\"URL\" data-id=\"https:\/\/hal.science\/hal-04549245\">https:\/\/hal.science\/hal-04549245<\/a><\/li><li>L\u00e9o Pradels, Silviu-Ioan Filip, Olivier Sentieys, Daniel Chillet, Thibaut Le Calloch. FPGA-based CNN Acceleration using Pattern-Aware Pruning, <em>in proceeding of the 6th IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS)<\/em>, Apr 2024, Abu Dhabi, UAE. <a href=\"https:\/\/ieeexplore.ieee.org\/document\/10595865\">https:\/\/ieeexplore.ieee.org\/document\/10595865<\/a><\/li><li>El-Mehdi El Arar, Massimiliano Fasi, Silviu-Ioan Filip, Mantas Mikaitis. Probabilistic error analysis of limited-precision stochastic rounding, 2024, preprint available at <a href=\"https:\/\/hal.science\/hal-04665809\">https:\/\/hal.science\/hal-04665809<\/a><\/li><\/ul>\n","protected":false},"excerpt":{"rendered":"<p>2021 Mariko Tatsumi, Yuxiang Xie, Caroline White, Silviu-Ioan Filip, Olivier Sentieys, et al. MPTorch and MPArchimedes: Open Source Frameworks to Explore Custom Mixed-Precision Operations for\u2026<\/p>\n<p> <a class=\"continue-reading-link\" href=\"https:\/\/project.inria.fr\/leanai\/publications\/\"><span>Continue reading<\/span><i class=\"crycon-right-dir\"><\/i><\/a> <\/p>\n","protected":false},"author":1754,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-71","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/project.inria.fr\/leanai\/wp-json\/wp\/v2\/pages\/71","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/project.inria.fr\/leanai\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/project.inria.fr\/leanai\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/project.inria.fr\/leanai\/wp-json\/wp\/v2\/users\/1754"}],"replies":[{"embeddable":true,"href":"https:\/\/project.inria.fr\/leanai\/wp-json\/wp\/v2\/comments?post=71"}],"version-history":[{"count":14,"href":"https:\/\/project.inria.fr\/leanai\/wp-json\/wp\/v2\/pages\/71\/revisions"}],"predecessor-version":[{"id":138,"href":"https:\/\/project.inria.fr\/leanai\/wp-json\/wp\/v2\/pages\/71\/revisions\/138"}],"wp:attachment":[{"href":"https:\/\/project.inria.fr\/leanai\/wp-json\/wp\/v2\/media?parent=71"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}