{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:10:27Z","timestamp":1740132627349,"version":"3.37.3"},"reference-count":26,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-009"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-001"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computer"],"published-print":{"date-parts":[[2020,6]]},"DOI":"10.1109\/mc.2020.2984870","type":"journal-article","created":{"date-parts":[[2020,6,3]],"date-time":"2020-06-03T20:22:22Z","timestamp":1591215742000},"page":"73-76","source":"Crossref","is-referenced-by-count":1,"title":["Inference Acceleration: Adding Brawn to the Brains"],"prefix":"10.1109","volume":"53","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5415-6631","authenticated-orcid":false,"given":"Mark","family":"Campbell","sequence":"first","affiliation":[{"name":"Trace3"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Knowledge distillation Simplified","year":"2019","author":"ganesh","key":"ref10"},{"article-title":"TinyBERT: Distilling BERT for natural language understanding","year":"2019","author":"jiao","key":"ref11"},{"journal-title":"Pruning deep neural networks","year":"2019","author":"singh","key":"ref12"},{"article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","year":"2018","author":"frankle","key":"ref13"},{"journal-title":"Model quantization for production-level neural network inference","year":"2019","author":"zhao","key":"ref14"},{"journal-title":"Deep learning deployment with NVIDIA TensorRT","year":"2019","author":"prasanna","key":"ref15"},{"journal-title":"XLA Optimizing Compiler for Machine Learning","year":"2020","key":"ref16"},{"journal-title":"private communication","year":"2020","author":"narasimhan","key":"ref17"},{"journal-title":"An in-depth look at Googles first Tensor Processing Unit (TPU)","year":"2017","author":"sato","key":"ref18"},{"key":"ref19","article-title":"Intel&#x2019;s neuromorphic nose learns scents in just one sniff","author":"moore","year":"2020","journal-title":"IEEE Spectrum"},{"journal-title":"AI and Compute","year":"2018","key":"ref4"},{"journal-title":"Microsoft trains world&#x2019;s largest Transformer language model","year":"2020","author":"johnson","key":"ref3"},{"journal-title":"Edge computing market outlook 2025","year":"2019","author":"sinnarkar","key":"ref6"},{"journal-title":"42 Years of Microprocessor Trend Data","year":"2020","author":"rupp","key":"ref5"},{"journal-title":"Deep learning has a size problem","year":"2019","author":"toole","key":"ref8"},{"journal-title":"The Digitization of the World From Edge to Core","year":"2018","author":"reinsel","key":"ref7"},{"journal-title":"Nvidia trains world&#x2019;s largest Transformer-based language model","year":"2019","author":"johnson","key":"ref2"},{"article-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","year":"2016","author":"iandola","key":"ref9"},{"journal-title":"OpenAI releases curtailed version of GPT-2 language model","year":"2019","author":"johnson","key":"ref1"},{"journal-title":"Amazon sticks AI inference chip up for rent in the cloud for machine-learning geeks","year":"2019","author":"quach","key":"ref20"},{"key":"ref22","article-title":"Facebook plans to develop its own AI chips","author":"shead","year":"2019","journal-title":"Forbes"},{"key":"ref21","article-title":"Microsoft sends a new kind of AI processor into the cloud","author":"knight","year":"2019","journal-title":"Wired"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322255"},{"journal-title":"private communication","year":"2020","author":"sharify","key":"ref23"},{"journal-title":"BERT explained State of the art language model for NLP","year":"2018","author":"horev","key":"ref26"},{"journal-title":"private communication","year":"2020","author":"harris","key":"ref25"}],"container-title":["Computer"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/2\/9107270\/09107275.pdf?arnumber=9107275","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,5]],"date-time":"2022-05-05T20:02:54Z","timestamp":1651780974000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9107275\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6]]},"references-count":26,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/mc.2020.2984870","relation":{},"ISSN":["0018-9162","1558-0814"],"issn-type":[{"type":"print","value":"0018-9162"},{"type":"electronic","value":"1558-0814"}],"subject":[],"published":{"date-parts":[[2020,6]]}}}