{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T16:48:53Z","timestamp":1781110133131,"version":"3.54.1"},"reference-count":62,"publisher":"IGI Global Scientific Publishing","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,10]]},"abstract":"<jats:p>This study investigates the effectiveness of multiple maxout activation variants on image classification, facial identification and verification tasks using convolutional neural networks. A network with maxout activation has a higher number of trainable parameters compared to networks with traditional activation functions. However, it is not clear if the activation function itself or the increase in the number of trainable parameters is responsible for yielding the best performance on different entity recognition tasks. This article investigates if an increase in the number of convolutional filters on the rectified linear unit activation performs equal-to or better-than maxout networks. Our experiments compare rectified linear unit, leaky rectified linear unit, scaled exponential linear unit, and hyperbolic tangent to four maxout variants. Throughout the experiments, we found that on average, across all datasets, the rectified linear unit networks perform better than any maxout activation when the number of convolutional filters is increased six times.<\/jats:p>","DOI":"10.4018\/ijmdem.2019100101","type":"journal-article","created":{"date-parts":[[2019,12,12]],"date-time":"2019-12-12T15:05:17Z","timestamp":1576163117000},"page":"1-25","source":"Crossref","is-referenced-by-count":4,"title":["Maxout Networks for Visual Recognition"],"prefix":"10.4018","volume":"10","author":[{"given":"Gabriel","family":"Castaneda","sequence":"first","affiliation":[{"name":"Florida Atlantic University, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul","family":"Morris","sequence":"additional","affiliation":[{"name":"Florida Atlantic University, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taghi M","family":"Khoshgoftaar","sequence":"additional","affiliation":[{"name":"Florida Atalntic University, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"2432","reference":[{"key":"IJMDEM.2019100101-0","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., . . . Ghemawat, S. (2016). Tensorflow: Large-scale machine learning on heterogeneous distributed systems."},{"key":"IJMDEM.2019100101-1","author":"M. L.Berenson","year":"1983","journal-title":"Intermediate Statistical Methods and Applications: A Computer Package Approach"},{"key":"IJMDEM.2019100101-2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707745"},{"key":"IJMDEM.2019100101-3","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00020"},{"key":"IJMDEM.2019100101-4","first-page":"135","article-title":"Deep Learning with Maxout Activations for Visual Recognition and Verification.","author":"G.Castaneda","year":"2019","journal-title":"Proceedings of the IEEE 20th International Conference on Information Reuse and Integration for Data Science (IRI)"},{"key":"IJMDEM.2019100101-5","unstructured":"Chang, J., & Chen, Y. (2015). Batch-normalized maxout network in network."},{"key":"IJMDEM.2019100101-6","author":"F.Chollet","year":"2015"},{"key":"IJMDEM.2019100101-7","unstructured":"Dean, J., Corrado, G., Monga, R., Chen, K., Devin, M., Mao, M., . . . Le, Q. V. (2012). Large scale distributed deep networks. In Advances in neural information processing systems (pp. 1223-1231). Academic Press."},{"key":"IJMDEM.2019100101-8","doi-asserted-by":"publisher","DOI":"10.1109\/IST.2016.7738244"},{"key":"IJMDEM.2019100101-9","unstructured":"Goodfellow, I., Bulatov, Y., Ibarz, J., Arnoud, S., & Shet, V. (2013). Multi-digit number recognition from street view imagery using deep convolutional neural networks."},{"key":"IJMDEM.2019100101-10","article-title":"An empirical investigation of catastrophic forgetting in gradient-based neural networks.","author":"I.Goodfellow","year":"2014","journal-title":"Proceedings of the International Conference on Learning Representations (ICLR)"},{"key":"IJMDEM.2019100101-11","article-title":"Maxout Networks.","author":"I.Goodfellow","year":"2013","journal-title":"Proceedings of the 30th International Conference on Machine Learning (ICML 2013)"},{"key":"IJMDEM.2019100101-12","unstructured":"Google. (n.d.). Google Images. Retrieved from https:\/\/images.google.com\/"},{"key":"IJMDEM.2019100101-13","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1007\/978-0-387-73003-5_192","article-title":"Face Databases and Evaluation","author":"D.Gorodnichy","year":"2009","journal-title":"Encyclopedia of Biometrics"},{"key":"IJMDEM.2019100101-14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_6"},{"key":"IJMDEM.2019100101-15","unstructured":"Hammer, B. (2019, 9 1). Popular datasets over time. Kaggle. Retrieved from https:\/\/www.kaggle.com\/benhamner\/popular-datasets-over-time\/code"},{"key":"IJMDEM.2019100101-16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"IJMDEM.2019100101-17","article-title":"Everything Counts: A Taxonomy of Deep Learning Approaches for Object Counting.","author":"K.Heinrich","year":"2019","journal-title":"Proceedings of the 27th European Conference on Information Systems"},{"key":"IJMDEM.2019100101-18","author":"G.Huang","year":"2007","journal-title":"Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments"},{"key":"IJMDEM.2019100101-19","first-page":"1883","article-title":"Stacked progressive auto-encoders (spae) for face recognition across poses.","author":"M.Kan","year":"2014","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"IJMDEM.2019100101-20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.527"},{"key":"IJMDEM.2019100101-21","first-page":"971","article-title":"Self-normalizing neural networks","author":"G.Klambauer","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"IJMDEM.2019100101-22","author":"A.Krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images"},{"key":"IJMDEM.2019100101-23","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"A.Krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems"},{"key":"IJMDEM.2019100101-24","unstructured":"LeCun, Y., & Bengio, Y. (1995). Convolutional networks for images, speech, and time series."},{"key":"IJMDEM.2019100101-25","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"IJMDEM.2019100101-26","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-013-0198-9"},{"key":"IJMDEM.2019100101-27","unstructured":"Li, Y., Ding, P., & Li, B. (2018). Training Neural Networks by Using Power Linear Units (PoLUs)."},{"key":"IJMDEM.2019100101-28","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477624"},{"key":"IJMDEM.2019100101-29","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.08.037"},{"key":"IJMDEM.2019100101-30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0876-z"},{"key":"IJMDEM.2019100101-31","article-title":"Network in Network.","author":"M.Lin","year":"2014","journal-title":"Proceedings of the International Conference on Learning Representations (ICLR)"},{"key":"IJMDEM.2019100101-32","first-page":"3431","article-title":"Fully convolutional networks for semantic segmentation.","author":"J.Long","year":"2015","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"IJMDEM.2019100101-33","first-page":"3","article-title":"Rectifier nonlinearities improve neural network acoustic models.","author":"A.Maas","year":"2013","journal-title":"Proceedings of the International Conference on Machine Learning (ICML)"},{"key":"IJMDEM.2019100101-34","unstructured":"MATLAB. (2010). MATLAB version 8.1.0.604 (R2016a)."},{"key":"IJMDEM.2019100101-35","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.05.007"},{"key":"IJMDEM.2019100101-36","doi-asserted-by":"publisher","DOI":"10.1145\/2671188.2749391"},{"key":"IJMDEM.2019100101-37","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines.","author":"V.Nair","year":"2010","journal-title":"Proceedings of the 27th international conference on machine learning (ICML-10)"},{"key":"IJMDEM.2019100101-38","article-title":"Reading digits in natural images with unsupervised feature learning.","author":"Y.Netzer","year":"2011","journal-title":"NIPS Workshop on Deep Learning and Unsupervised Feature Learning"},{"key":"IJMDEM.2019100101-39","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2014.7025068"},{"key":"IJMDEM.2019100101-40","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacr.2017.08.027"},{"key":"IJMDEM.2019100101-41","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-015-0744-0"},{"key":"IJMDEM.2019100101-42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461436"},{"key":"IJMDEM.2019100101-43","doi-asserted-by":"crossref","unstructured":"Parkhi, O., Vedaldi, A., & Zisserman, A. (2015). Deep face recognition. bmvc, 1(3), 6.","DOI":"10.5244\/C.29.41"},{"key":"IJMDEM.2019100101-44","doi-asserted-by":"publisher","DOI":"10.1016\/S0262-8856(97)00070-X"},{"key":"IJMDEM.2019100101-45","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"IJMDEM.2019100101-46","first-page":"815","article-title":"Facenet: A unified embedding for face recognition and clustering.","author":"F.Schroff","year":"2015","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"issue":"1","key":"IJMDEM.2019100101-47","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting.","volume":"15","author":"N.Srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"IJMDEM.2019100101-48","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296993"},{"key":"IJMDEM.2019100101-49","doi-asserted-by":"publisher","DOI":"10.1007\/s12194-017-0406-5"},{"key":"IJMDEM.2019100101-50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855088"},{"key":"IJMDEM.2019100101-51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.214"},{"key":"IJMDEM.2019100101-52","doi-asserted-by":"publisher","DOI":"10.2307\/3001913"},{"key":"IJMDEM.2019100101-53","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00824"},{"key":"IJMDEM.2019100101-54","doi-asserted-by":"crossref","unstructured":"Viola, P., & Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. CVPR, 1(511-518), 3.","DOI":"10.1109\/CVPR.2001.990517"},{"key":"IJMDEM.2019100101-55","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/7068349"},{"key":"IJMDEM.2019100101-56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_31"},{"key":"IJMDEM.2019100101-57","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2018.2833032"},{"key":"IJMDEM.2019100101-58","unstructured":"Xiao, H., Rasul, K., & Vollgraf, R. (2017). Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms."},{"key":"IJMDEM.2019100101-59","unstructured":"Xu, B., Wang, N., Chen, T., & Li, M. (2015). Empirical evaluation of rectified activations in convolutional network."},{"key":"IJMDEM.2019100101-60","doi-asserted-by":"publisher","DOI":"10.1186\/s13640-018-0379-2"},{"key":"IJMDEM.2019100101-61","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"}],"container-title":["International Journal of Multimedia Data Engineering and Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.igi-global.com\/viewtitle.aspx?TitleId=245261","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,6]],"date-time":"2022-05-06T04:16:49Z","timestamp":1651810609000},"score":1,"resource":{"primary":{"URL":"http:\/\/services.igi-global.com\/resolvedoi\/resolve.aspx?doi=10.4018\/IJMDEM.2019100101"}},"subtitle":[""],"short-title":[],"issued":{"date-parts":[[2019,10]]},"references-count":62,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.4018\/ijmdem.2019100101","relation":{},"ISSN":["1947-8534","1947-8542"],"issn-type":[{"value":"1947-8534","type":"print"},{"value":"1947-8542","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,10]]}}}