{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T15:58:50Z","timestamp":1756310330090,"version":"3.38.0"},"reference-count":13,"publisher":"SAGE Publications","issue":"6","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IDA"],"published-print":{"date-parts":[[2022,11,12]]},"abstract":"<jats:p>In this study, we develop a penalized additive regression estimation method based on a neural network architecture. An additive neural network model is constructed by using a linear combination of univariate neural networks, or equivalently functional components. We use a B-spline activation function, which is useful to capture local features of data, for nodes that constitute the model. A penalty function is adopted to induce sparsity in functional components and nodes on each component simultaneously. This enables us to obtain a sparse representation, which in turn improves accountability of the model. To implement the proposed estimation method, we devise an efficient iterative algorithm based on a coordinate-wise updating process. An initialization scheme specialized for the B-spline activation function is proposed. The initialization approach enables the proposed method to achieve better performance compared with random initialization scheme. Numerical studies show that the fitted functional components of our estimator adapt to local and sparse structures based on a given dataset.<\/jats:p>","DOI":"10.3233\/ida-216070","type":"journal-article","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T15:33:01Z","timestamp":1667575981000},"page":"1597-1616","source":"Crossref","is-referenced-by-count":2,"title":["Penalized additive neural network regression"],"prefix":"10.1177","volume":"26","author":[{"given":"Jae-Kyung","family":"Shin","sequence":"first","affiliation":[{"name":"Department of Statistics, Korea University, Seoul, Korea"}]},{"given":"Kwan-Young","family":"Bak","sequence":"additional","affiliation":[{"name":"School of Mathematics, Statistics and Data Science, SungShin Women\u2019s University, Seoul, Korea"},{"name":"Data Science Center, SungShin Women\u2019s University, Seoul, Korea"}]},{"given":"Ja-Yong","family":"Koo","sequence":"additional","affiliation":[{"name":"Department of Statistics, Korea University, Seoul, Korea"}]}],"member":"179","reference":[{"issue":"4","key":"10.3233\/IDA-216070_ref2","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1080\/00401706.2012.726000","article-title":"Variable selection in additive models using p-splines","volume":"54","author":"Antoniadis","year":"2012","journal-title":"Technometrics"},{"issue":"4","key":"10.3233\/IDA-216070_ref3","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1080\/00401706.1995.10484371","article-title":"Better subset regression using the nonnegative garrote","volume":"37","author":"Breiman","year":"1995","journal-title":"Technometrics"},{"unstructured":"X. Glorot and Y. Bengio, Understanding the difficulty of training deep feedforward neural networks, in: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pages 249\u2013256, JMLR Workshop and Conference Proceedings, 2010.","key":"10.3233\/IDA-216070_ref4"},{"doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren and J. Sun, Delving deep into rectifiers: Surpassing human-level performance on imagenet classification, in: Proceedings of the IEEE International Conference on Computer Vision, pages 1026\u20131034, 2015.","key":"10.3233\/IDA-216070_ref6","DOI":"10.1109\/ICCV.2015.123"},{"issue":"5","key":"10.3233\/IDA-216070_ref8","doi-asserted-by":"crossref","first-page":"2272","DOI":"10.1214\/009053606000000722","article-title":"Component selection and smoothing in multivariate nonparametric regression","volume":"34","author":"Lin","year":"2006","journal-title":"The Annals of Statistics"},{"doi-asserted-by":"crossref","unstructured":"W.J. Potts, Generalized additive neural networks, in: Proceedings of the Fifth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 194\u2013200, 1999.","key":"10.3233\/IDA-216070_ref9","DOI":"10.1145\/312129.312228"},{"issue":"2","key":"10.3233\/IDA-216070_ref11","doi-asserted-by":"crossref","first-page":"679","DOI":"10.5705\/ss.2011.030a","article-title":"Surface estimation, variable selection, and the nonparametric oracle property","volume":"21","author":"Storlie","year":"2011","journal-title":"Statistica Sinica"},{"issue":"1","key":"10.3233\/IDA-216070_ref12","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the lasso","volume":"58","author":"Tibshirani","year":"1996","journal-title":"Journal of the Royal Statistical Society: Series B (Methodological)"},{"issue":"484","key":"10.3233\/IDA-216070_ref14","doi-asserted-by":"crossref","first-page":"1556","DOI":"10.1198\/016214508000000788","article-title":"Variable selection in nonparametric varying-coefficient models for analysis of repeated measurements","volume":"103","author":"Wang","year":"2008","journal-title":"Journal of the American Statistical Association"},{"key":"10.3233\/IDA-216070_ref17","doi-asserted-by":"crossref","first-page":"108192","DOI":"10.1016\/j.patcog.2021.108192","article-title":"Gami-net: An explainable neural network based on generalized additive models with structured interactions","volume":"120","author":"Yang","year":"2021","journal-title":"Pattern Recognition"},{"issue":"6","key":"10.3233\/IDA-216070_ref18","doi-asserted-by":"crossref","first-page":"474","DOI":"10.1016\/j.cemconcomp.2007.02.001","article-title":"Modeling slump flow of concrete using second-order regressions and artificial neural networks","volume":"29","author":"Yeh","year":"2007","journal-title":"Cement and Concrete Composites"},{"issue":"1","key":"10.3233\/IDA-216070_ref19","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1111\/j.1467-9868.2005.00532.x","article-title":"Model selection and estimation in regression with grouped variables","volume":"68","author":"Yuan","year":"2006","journal-title":"Journal of the Royal Statistical Society: Series B (Statistical Methodology)"},{"issue":"4","key":"10.3233\/IDA-216070_ref20","doi-asserted-by":"crossref","first-page":"557","DOI":"10.4310\/SII.2010.v3.n4.a13","article-title":"Group variable selection via a hierarchical lasso and its oracle property","volume":"3","author":"Zhou","year":"2010","journal-title":"Statistics and Its Interface"}],"container-title":["Intelligent Data Analysis"],"original-title":[],"link":[{"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/content.iospress.com\/download?id=10.3233\/IDA-216070","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T05:11:43Z","timestamp":1741669903000},"score":1,"resource":{"primary":{"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/journals.sagepub.com\/doi\/full\/10.3233\/IDA-216070"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,12]]},"references-count":13,"journal-issue":{"issue":"6"},"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/doi.org\/10.3233\/ida-216070","relation":{},"ISSN":["1088-467X","1571-4128"],"issn-type":[{"type":"print","value":"1088-467X"},{"type":"electronic","value":"1571-4128"}],"subject":[],"published":{"date-parts":[[2022,11,12]]}}}