{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T23:46:26Z","timestamp":1740181586089,"version":"3.37.3"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2021,5,8]],"date-time":"2021-05-08T00:00:00Z","timestamp":1620432000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,5,8]],"date-time":"2021-05-08T00:00:00Z","timestamp":1620432000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/100000774","name":"Defense Threat Reduction Agency","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000774","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Science Foundation","award":["CCF-1763747"],"award-info":[{"award-number":["CCF-1763747"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SN COMPUT. SCI."],"published-print":{"date-parts":[[2021,7]]},"DOI":"10.1007\/s42979-021-00646-0","type":"journal-article","created":{"date-parts":[[2021,5,8]],"date-time":"2021-05-08T15:02:27Z","timestamp":1620486147000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Deep-n-Cheap: An Automated Efficient and Extensible Search Framework for Cost-Effective Deep Learning"],"prefix":"10.1007","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3084-1428","authenticated-orcid":false,"given":"Sourya","family":"Dey","sequence":"first","affiliation":[]},{"given":"Sara","family":"Babakniya","sequence":"additional","affiliation":[]},{"given":"Saikrishna C.","family":"Kanala","sequence":"additional","affiliation":[]},{"given":"Marco","family":"Paolieri","sequence":"additional","affiliation":[]},{"given":"Leana","family":"Golubchik","sequence":"additional","affiliation":[]},{"given":"Peter A.","family":"Beerel","sequence":"additional","affiliation":[]},{"given":"Keith M.","family":"Chugg","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,5,8]]},"reference":[{"key":"646_CR1","unstructured":"AWSLabs: AutoGluon: AutoML toolkit for deep learning. https:\/\/autogluon.mxnet.io\/# (2020).\u00a0Accessed 1 Jul 2020."},{"key":"646_CR2","unstructured":"Baker B, Gupta O, Naik N, Raskar R. Designing neural network architectures using reinforcement learning. In: Proc. ICLR, 2017."},{"key":"646_CR3","unstructured":"Baker B, Gupta O, Raskar R, Naik N. Accelerating neural architecture search using performance prediction. In: Proc. ICLR, 2017."},{"key":"646_CR4","doi-asserted-by":"publisher","first-page":"4308","DOI":"10.1038\/ncomms5308","volume":"5","author":"P Baldi","year":"2014","unstructured":"Baldi P, Sadowski P, Whiteson D. Searching for exotic particles in high-energy physics with deep learning. Nat Commun. 2014;5:4308.","journal-title":"Nat Commun"},{"key":"646_CR5","unstructured":"Bergstra J, Yamins D, Cox DD. Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures. In: Proc. ICML, 2013; pp. I-115\u2013I-123."},{"key":"646_CR6","unstructured":"Brochu E, Cora VM, de\u00a0Freitas N. A tutorial on Bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning. arXiv preprint arXiv:1012.2599. 2010."},{"key":"646_CR7","unstructured":"Cai H, Dey S. Private communication with ProxylessNAS authors. 2020. We (the authors of this paper) corresponded with the authors of ProxylessNAS via email in March 2020."},{"key":"646_CR8","unstructured":"Cai H, Dey S. Private communication with ProxylessNAS authors. 2020. We (the authors of this paper) corresponded with the authors of ProxylessNAS via email in March 2020."},{"key":"646_CR9","unstructured":"Cai H, Zhu L, Han S. ProxylessNAS: direct neural architecture search on target task and hardware. In: Proc. ICLR, 2019."},{"issue":"2","key":"646_CR10","first-page":"332","volume":"9","author":"S Dey","year":"2019","unstructured":"Dey S, Huang KW, Beerel PA, Chugg KM. Pre-defined sparse neural networks with hardware acceleration. IEEE JETCAS. 2019;9(2):332\u201345.","journal-title":"IEEE JETCAS"},{"key":"646_CR11","unstructured":"Dey S, Kanala SC, Chugg KM, Beerel PA. Deep-n-Cheap: an automated search framework for low complexity deep learning. In: Proc. ACML, 2020; pp. 273\u2013288."},{"key":"646_CR12","doi-asserted-by":"crossref","unstructured":"Dey S, Shao Y, Chugg K, Beerel P. Accelerating training of deep neural networks via sparse edge processing. In: Proc. ICANN, 2017; pp. 273\u2013280.","DOI":"10.1007\/978-3-319-68600-4_32"},{"key":"646_CR13","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. arXiv preprint arXiv:1512.03385. 2015.","DOI":"10.1109\/CVPR.2016.90"},{"key":"646_CR14","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Identity mappings in deep residual networks. CoRR abs\/1603.05027. 2016.","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"646_CR15","unstructured":"He Y, Lin J, et\u00a0al. AMC: AutoML for model compression and acceleration on mobile devices. In: Proc. ECCV, 2018; pp. 784\u2013800."},{"key":"646_CR16","doi-asserted-by":"crossref","unstructured":"Huang G, Sun Y, et\u00a0al. Deep networks with stochastic depth. In: Proc. ECCV, 2016; pp. 646\u2013661.","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"646_CR17","unstructured":"Hutter F, Osborne MA. A kernel for hierarchical parameter spaces. arXiv preprint arXiv:1310.5738. 2013."},{"key":"646_CR18","unstructured":"Jin H. Comment on \u2018not able to load best automodel after saving\u2019 issue. https:\/\/github.com\/keras-team\/autokeras\/issues\/966#issuecomment-594590617 (2019). Accessed 1 Apr 2020."},{"key":"646_CR19","doi-asserted-by":"crossref","unstructured":"Jin H, Song Q, Hu X. Auto-keras: an efficient neural architecture search system. In: Proc. KDD, 2019; pp. 1946\u20131956.","DOI":"10.1145\/3292500.3330648"},{"key":"646_CR20","doi-asserted-by":"crossref","unstructured":"Johnson R, Zhang T. Effective use of word order for text categorization with convolutional neural networks. In: Proc. NAACL, 2015; pp. 103\u2013112.","DOI":"10.3115\/v1\/N15-1011"},{"key":"646_CR21","doi-asserted-by":"crossref","unstructured":"Johnson R, Zhang T. Deep pyramid convolutional neural networks for text categorization. In: Proc. ACL, 2017; pp. 562\u2013570.","DOI":"10.18653\/v1\/P17-1052"},{"key":"646_CR22","unstructured":"Kandasamy K, Neiswanger W, et\u00a0al. Neural architecture search with Bayesian optimisation and optimal transport. In: Proc. NeurIPS, 2018; pp. 2020\u20132029."},{"key":"646_CR23","unstructured":"Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. In: Proc. NeurIPS, 2012; pp. 1097\u20131105."},{"key":"646_CR24","doi-asserted-by":"crossref","unstructured":"Liu C, Zoph B, et\u00a0al. Progressive neural architecture search. In: Proc. ECCV, 2018; pp. 19\u201335.","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"646_CR25","unstructured":"Liu H, Simonyan K, Yang Y. DARTS: differentiable architecture search. In: Proc. ICLR, 2019."},{"key":"646_CR26","doi-asserted-by":"publisher","first-page":"618","DOI":"10.1007\/s10278-018-0168-6","volume":"32","author":"RC Mayo","year":"2019","unstructured":"Mayo RC, Kent D, et al. Reduction of false-positive markings on mammograms: a retrospective comparison study using an artificial intelligence-based CAD. J Dig Imaging. 2019;32:618\u201324.","journal-title":"J Dig Imaging"},{"key":"646_CR27","unstructured":"Mendoza H, Klein A, et\u00a0al. Towards automatically-tuned deep neural networks. In: AutoML: methods, systems, challenges, chap.\u00a07, 2018; pp. 141\u2013156."},{"key":"646_CR28","doi-asserted-by":"crossref","unstructured":"Miikkulainen R, Liang J, et\u00a0al. Evolving deep neural networks. In: Artificial intelligence in the age of neural networks and brain computing, chap.\u00a015, pp. 293 \u2013 312. Academic Press; 2019.","DOI":"10.1016\/B978-0-12-815480-9.00015-3"},{"key":"646_CR29","unstructured":"Page D. How to train your ResNet. https:\/\/myrtle.ai\/how-to-train-your-resnet\/ (2019).\u00a0Accessed 1 Apr 2020."},{"key":"646_CR30","unstructured":"Pham H, Guan M, et\u00a0al. Efficient neural architecture search via parameter sharing. In: Proc. ICML, 2018; pp. 4095\u20134104."},{"key":"646_CR31","doi-asserted-by":"crossref","unstructured":"Real E, Aggarwal A, Huang Y, Le QV. Regularized evolution for image classifier architecture search. In: Proc. AAAI, 2019; pp. 4780\u20134789.","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"646_CR32","unstructured":"Santana E, Hotz G. Learning a driving simulator. arXiv preprint arXiv:1608.01230. 2016."},{"key":"646_CR33","unstructured":"Snoek J, Larochelle H, Adams RP. Practical Bayesian optimization of machine learning algorithms. In: Proc. NeurIPS, 2012; pp. 2951\u20132959."},{"key":"646_CR34","unstructured":"Swersky K, Duvenaud D et\u00a0al. Raiders of the lost architecture: Kernels for Bayesian optimization in conditional parameter spaces. In: NeurIPS workshop on Bayesian optimization in theory and practice. 2013."},{"key":"646_CR35","unstructured":"Tan M, Le QV. Efficientnet: rethinking model scaling for convolutional neural networks. arXiv preprint arXiv:1905.11946. 2019."},{"key":"646_CR36","doi-asserted-by":"crossref","unstructured":"Thornton C, Hutter F, Hoos HH, Leyton-Brown K. Auto-WEKA: combined selection and hyperparameter optimization of classification algorithms. In: Proc. KDD, 2013; pp. 847\u2014-855.","DOI":"10.1145\/2487575.2487629"},{"key":"646_CR37","doi-asserted-by":"crossref","unstructured":"Xie L, Yuille A. Genetic CNN. In: Proc. ICCV, 2017; pp. 1388\u20131397.","DOI":"10.1109\/ICCV.2017.154"},{"key":"646_CR38","unstructured":"Xie S, Zheng H, Liu C, Lin L. SNAS: stochastic neural architecture search. In: Proc. ICLR, 2019."},{"key":"646_CR39","unstructured":"Yang Z, Dai Z, Yang Y, Carbonell JG, Salakhutdinov R, Le QV. XLNet: generalized autoregressive pretraining for language understanding. In: NIPS, 2019; pp. 5754\u20135764."},{"key":"646_CR40","doi-asserted-by":"crossref","unstructured":"Zagoruyko S, Komodakis N. Wide residual networks. In: Proc. BMVC, 2016; pp. 87.1\u201387.12.","DOI":"10.5244\/C.30.87"},{"key":"646_CR41","unstructured":"Zhang X, Zhao JJ, LeCun, Y. Character-level convolutional networks for text classification. arXiv preprint arXiv:1509.01626. 2015."},{"key":"646_CR42","doi-asserted-by":"crossref","unstructured":"Zoph B, Vasudevan V, Shlens J, Le QV. Learning transferable architectures for scalable image recognition. In: Proc. CVPR, 2018; pp. 8697\u20138710.","DOI":"10.1109\/CVPR.2018.00907"},{"key":"646_CR43","doi-asserted-by":"crossref","unstructured":"Kundu S, Nazemi M, Pedram M, Chugg KM, Beerel PA. Pre-Defined Sparsity for Low-Complexity Convolutional Neural Networks. IEEE Transactions on Computers. 2020;69(7):1045\u201358.","DOI":"10.1109\/TC.2020.2972520"}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-021-00646-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-021-00646-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-021-00646-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,30]],"date-time":"2024-08-30T12:37:23Z","timestamp":1725021443000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-021-00646-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,8]]},"references-count":43,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,7]]}},"alternative-id":["646"],"URL":"https:\/\/doi.org\/10.1007\/s42979-021-00646-0","relation":{},"ISSN":["2662-995X","2661-8907"],"issn-type":[{"type":"print","value":"2662-995X"},{"type":"electronic","value":"2661-8907"}],"subject":[],"published":{"date-parts":[[2021,5,8]]},"assertion":[{"value":"22 February 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 April 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 May 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"On behalf of all authors, the corresponding author states that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}],"article-number":"265"}}