{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:38:26Z","timestamp":1740101906897,"version":"3.37.3"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,11]],"date-time":"2023-06-11T00:00:00Z","timestamp":1686441600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,11]],"date-time":"2023-06-11T00:00:00Z","timestamp":1686441600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100018693","name":"Horizon Europe","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018693","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,11]]},"DOI":"10.1109\/aicas57966.2023.10168577","type":"proceedings-article","created":{"date-parts":[[2023,7,7]],"date-time":"2023-07-07T18:24:30Z","timestamp":1688754270000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["Free Bits: Latency Optimization of Mixed-Precision Quantized Neural Networks on the Edge"],"prefix":"10.1109","author":[{"given":"Georg","family":"Rutishauser","sequence":"first","affiliation":[{"name":"ETH Zürich,Departement Informationstechnologie und Elektrotechnik,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francesco","family":"Conti","sequence":"additional","affiliation":[{"name":"Università di Bologna,Dipartimento di Ingegneria Dell’Energia Elettrica e Dell’Informazione,Bologna,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luca","family":"Benini","sequence":"additional","affiliation":[{"name":"ETH Zürich,Departement Informationstechnologie und Elektrotechnik,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"year":"2022","key":"ref1","article-title":"Number of internet of things (iot) connected devices worldwide from 2019 to 2021, with forecasts from 2022 to 2030"},{"key":"ref2","article-title":"Memory-efficient Patch-based Inference for Tiny Deep Learning","author":"Lin","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref3","first-page":"517","article-title":"MicroNets: Neural Network Architectures for Deploying TinyML Applications on Commodity Microcontrollers","volume-title":"Proceedings of Machine Learning and Systems","author":"Banbury"},{"volume-title":"Armv8-M Architecture Reference Manual","key":"ref4"},{"key":"ref5","first-page":"348","article-title":"Accurate and Efficient 2-bit Quantized Neural Networks","volume-title":"Proceedings of Machine Learning and Systems","volume":"1","author":"Choi"},{"article-title":"Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights","volume-title":"International Conference on Learning Representations","author":"Zhou","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966166"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ESSCIRC53450.2021.9567767"},{"key":"ref9","first-page":"5741","article-title":"Bayesian bits: Unifying quantization and pruning","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"van Baalen","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00242"},{"key":"ref11","article-title":"BitPruning: Learning Bitlengths for Aggressive and Accurate Quantization","volume":"abs\/2002.0","author":"Nikolic","year":"2020","journal-title":"CoRR"},{"key":"ref12","first-page":"326","article-title":"Memory-Driven Mixed Low Precision Quantization for Enabling Deep Network Inference on Microcontrollers","volume-title":"Proceedings of Machine Learning and Systems","volume":"2","author":"Rusci"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IGSC55832.2022.9969373"},{"key":"ref14","first-page":"112","article-title":"Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networks","volume-title":"Proceedings of Machine Learning and Systems","author":"Jain"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1704.04861"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3066883"}],"event":{"name":"2023 IEEE 5th International Conference on Artificial Intelligence Circuits and Systems (AICAS)","start":{"date-parts":[[2023,6,11]]},"location":"Hangzhou, China","end":{"date-parts":[[2023,6,13]]}},"container-title":["2023 IEEE 5th International Conference on Artificial Intelligence Circuits and Systems (AICAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10168547\/10168548\/10168577.pdf?arnumber=10168577","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T22:30:52Z","timestamp":1710369052000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10168577\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,11]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/aicas57966.2023.10168577","relation":{},"subject":[],"published":{"date-parts":[[2023,6,11]]}}}