{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T13:11:15Z","timestamp":1740143475207,"version":"3.37.3"},"reference-count":17,"publisher":"Association for Computing Machinery (ACM)","issue":"5s","funder":[{"name":"Innovate UK HICLASS","award":["113213"]},{"DOI":"10.13039\/100000001","name":"US National Science Foundation","doi-asserted-by":"crossref","award":["CNS-2141256 and CPS-2229290"],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Embed. Comput. Syst."],"published-print":{"date-parts":[[2023,10,31]]},"abstract":"\n An\n IDK classifier<\/jats:italic>\n is a computing component that categorizes inputs into one of a number of classes, if it is able to do so with the required level of confidence, otherwise it returns \u201cI Don\u2019t Know\u201d (IDK).\n IDK classifier cascades<\/jats:italic>\n have been proposed as a way of balancing the needs for fast response and high accuracy in classification-based machine perception. Efficient algorithms for the synthesis of IDK classifier cascades have been derived; however, the responsiveness of these cascades is highly dependent on the accuracy of predictions regarding the run-time behavior of the classifiers from which they are built. Accurate predictions of such run-time behavior is difficult to obtain for many of the classifiers used for perception. By applying the\n algorithms using predictions<\/jats:italic>\n framework, we propose efficient algorithms for the synthesis of IDK classifier cascades that are\n robust<\/jats:italic>\n to inaccurate predictions in the following sense: the IDK classifier cascades synthesized by our algorithms have short expected execution durations when the predictions are accurate, and these expected durations increase only within specified bounds when the predictions are inaccurate.\n <\/jats:p>","DOI":"10.1145\/3609129","type":"journal-article","created":{"date-parts":[[2023,9,9]],"date-time":"2023-09-09T13:33:18Z","timestamp":1694266398000},"page":"1-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Optimal Synthesis of Robust IDK Classifier Cascades"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4541-3445","authenticated-orcid":false,"given":"Sanjoy","family":"Baruah","sequence":"first","affiliation":[{"name":"Washington University in St.\u00a0Louis, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5621-8816","authenticated-orcid":false,"given":"Alan","family":"Burns","sequence":"additional","affiliation":[{"name":"The University of York, UK"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5772-0928","authenticated-orcid":false,"given":"Robert Ian","family":"Davis","sequence":"additional","affiliation":[{"name":"The University of York, UK"}]}],"member":"320","published-online":{"date-parts":[[2023,9,9]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11241-023-09395-0"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3575757.3593649"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.4230\/LIPIcs.ECRTS.2023.3"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11241-022-09383-w"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3453417.3453425"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2018.2831227"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.5555\/1614191"},{"key":"e_1_3_2_9_2","article-title":"Deep residual learning for image recognition","volume":"1512","author":"He K.","year":"2015","unstructured":"K. He, X. Zhang, S. Ren, and J. Sun. 2015. Deep residual learning for image recognition. CoRR abs\/1512.03385 (2015). arXiv:1512.03385http:\/\/arxiv.org\/abs\/1512.03385","journal-title":"CoRR"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p16-1090"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/321738.321743"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1017\/9781108637435.037"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1017\/9781108637435"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/MILCOM55135.2022.10017612"},{"key":"e_1_3_2_16_2","first-page":"580","volume-title":"Proceedings of the Thirty-Fourth Conference on Uncertainty in Artificial Intelligence, UAI 2018, Monterey, California, USA, August 6\u201310, 2018","author":"Wang X.","year":"2018","unstructured":"X. Wang, Y. Luo, D. Crankshaw, A. Tumanov, F. Yu, and J. Gonzalez. 2018. IDK cascades: Fast deep learning by learning not to overthink. In Proceedings of the Thirty-Fourth Conference on Uncertainty in Artificial Intelligence, UAI 2018, Monterey, California, USA, August 6\u201310, 2018, Amir Globerson and Ricardo Silva (Eds.). AUAI Press, 580\u2013590. http:\/\/auai.org\/uai2018\/proceedings\/papers\/212.pdf"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/1347375.1347389"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS55097.2022.00036"}],"container-title":["ACM Transactions on Embedded Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3609129","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,9]],"date-time":"2023-09-09T13:34:48Z","timestamp":1694266488000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3609129"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,9]]},"references-count":17,"journal-issue":{"issue":"5s","published-print":{"date-parts":[[2023,10,31]]}},"alternative-id":["10.1145\/3609129"],"URL":"https:\/\/doi.org\/10.1145\/3609129","relation":{},"ISSN":["1539-9087","1558-3465"],"issn-type":[{"type":"print","value":"1539-9087"},{"type":"electronic","value":"1558-3465"}],"subject":[],"published":{"date-parts":[[2023,9,9]]},"assertion":[{"value":"2023-03-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-07-13","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-09-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}