{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,20]],"date-time":"2025-08-20T13:19:40Z","timestamp":1755695980826,"version":"3.40.5"},"reference-count":37,"publisher":"World Scientific Pub Co Pte Ltd","issue":"13","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Patt. Recogn. Artif. Intell."],"published-print":{"date-parts":[[2020,12,15]]},"abstract":"<jats:p> This paper applies a hybrid evolutionary approach to a convolutional neural network (CNN) and determines the number of layers and filters based on the application and user need. It integrates compact genetic algorithm with stochastic gradient descent (SGD) for simultaneously evolving structure and parameters of the CNN. It defines an effectual string representation for combining structure and parameters of the CNN. The compact genetic algorithm helps in the evolution of network structure by optimizing the number of convolutional layers and number of filters in each convolutional layer. At the same time, an optimal set of weight parameters of the network is obtained using the SGD law. This approach amalgamates exploration in network space by compact genetic algorithm and exploitation in weight space with SGD in an effective manner. The proposed approach also incorporates user-defined parameters in the cost function in an elegant manner which controls the network structure and hence the performance of the network based on the users need. The effectiveness of the proposed approach has been demonstrated on four benchmark datasets, namely MNIST, COIL-100, CIFAR-10 and CIFAR-100. The obtained results clearly demonstrate the potential of the proposed approach by evolving architectures based on the nature of the application and the need of the user. <\/jats:p>","DOI":"10.1142\/s021800142052014x","type":"journal-article","created":{"date-parts":[[2020,1,31]],"date-time":"2020-01-31T08:30:26Z","timestamp":1580459426000},"page":"2052014","source":"Crossref","is-referenced-by-count":4,"title":["Application and Need-Based Architecture Design of Deep Neural Networks"],"prefix":"10.1142","volume":"34","author":[{"family":"Soniya","sequence":"first","affiliation":[{"name":"Dayalbagh Educational Institute, Dayalbagh, Agra, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3743-5601","authenticated-orcid":false,"given":"Sandeep","family":"Paul","sequence":"additional","affiliation":[{"name":"Dayalbagh Educational Institute, Dayalbagh, Agra, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lotika","family":"Singh","sequence":"additional","affiliation":[{"name":"Dayalbagh Educational Institute, Dayalbagh, Agra, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"219","published-online":{"date-parts":[[2020,4,30]]},"reference":[{"key":"S021800142052014XBIB001","first-page":"106","volume-title":"Proc. 4th Japan-Australia Joint Workshop on Intelligent and Evolutionary Systems","author":"Abraham A.","year":"2000"},{"issue":"4","key":"S021800142052014XBIB002","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1109\/TEVC.2003.814633","volume":"7","author":"Ahn C. W.","year":"2003","journal-title":"IEEE Trans. Evol. Comput."},{"issue":"1","key":"S021800142052014XBIB003","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1007\/s10710-018-9339-y","volume":"20","author":"Assun\u00e7\u00e3o F.","year":"2019","journal-title":"Genet. Program. Evol. Mach."},{"key":"S021800142052014XBIB004","first-page":"1","volume-title":"5th Int. Conf. Learning Representations (ICLR) Conference Track Proceedings","author":"Baker B.","year":"2017"},{"key":"S021800142052014XBIB005","doi-asserted-by":"crossref","first-page":"1301","DOI":"10.1007\/s13042-018-0811-z","volume":"10","author":"Banharnsakun A.","year":"2019","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"S021800142052014XBIB009","first-page":"1","volume-title":"7th Int. Conf. Learning Representations (ICLR)","author":"Elsken T.","year":"2019"},{"issue":"4","key":"S021800142052014XBIB010","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1109\/4235.797971","volume":"3","author":"Harik G. R.","year":"1999","journal-title":"IEEE Trans. Evol. Comput."},{"volume-title":"2016 IEEE Conf. Computer Vision and Pattern Recognition, CVPR 2016","author":"He K.","first-page":"770","key":"S021800142052014XBIB011"},{"key":"S021800142052014XBIB012","series-title":"Lecture Notes in Computer Science","volume-title":"Neural Networks: Tricks of the Trade","volume":"7700","author":"Hinton G. E.","year":"2012","edition":"2"},{"key":"S021800142052014XBIB013","doi-asserted-by":"crossref","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","volume":"18","author":"Hinton G. E.","year":"2006","journal-title":"Neural Comput."},{"key":"S021800142052014XBIB014","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"Hinton G. E.","year":"2006","journal-title":"Science"},{"volume-title":"22nd Int. Conf. Pattern Recognition","author":"Huang P.","first-page":"1532","key":"S021800142052014XBIB015"},{"key":"S021800142052014XBIB016","doi-asserted-by":"crossref","first-page":"2261","DOI":"10.1109\/CVPR.2017.243","volume-title":"2017 IEEE Conf. Computer Vision and Pattern Recognition (CVPR)","author":"Huang G.","year":"2017"},{"issue":"57","key":"S021800142052014XBIB017","volume":"89","author":"Jaafra Y.","year":"2019","journal-title":"Image Vision Comput."},{"key":"S021800142052014XBIB018","doi-asserted-by":"crossref","first-page":"1946","DOI":"10.1145\/3292500.3330648","volume-title":"Proc. 25th ACM SIGKDD Int. Conf. Knowledge Discovery & Data Mining, KDD \u201919","author":"Jin H.","year":"2019"},{"key":"S021800142052014XBIB020","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1007\/978-3-030-05318-5_4","volume-title":"Automated Machine Learning: Methods, Systems, Challenges","author":"Kotthoff L.","year":"2019"},{"key":"S021800142052014XBIB022","first-page":"255","volume-title":"The Handbook of Brain Theory and Neural Networks","author":"LeCun Y.","year":"1995"},{"key":"S021800142052014XBIB023","first-page":"306","volume-title":"Intelligent Signal Processing","volume":"86","author":"LeCun Y.","year":"2001"},{"key":"S021800142052014XBIB026","first-page":"6391","volume-title":"Proc. 32nd Int. Conf. Neural Information Processing Systems, NIPS\u201918","author":"Li H.","year":"2018"},{"key":"S021800142052014XBIB027","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1016\/B978-0-12-815480-9.00015-3","volume-title":"Artificial Intelligence in the Age of Neural Networks and Brain Computing","author":"Miikkulainen R.","year":"2019"},{"key":"S021800142052014XBIB029","first-page":"8024","volume-title":"Advances in Neural Information Processing Systems 32","author":"Paszke A.","year":"2017"},{"issue":"6088","key":"S021800142052014XBIB032","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","volume":"323","author":"Rumelhart D. E.","year":"1986","journal-title":"Nature"},{"key":"S021800142052014XBIB033","doi-asserted-by":"crossref","DOI":"10.1007\/s11263-015-0816-y","volume-title":"ImageNet Large Scale Visual Recognition Challenge","author":"Russakovsky O.","year":"2015"},{"key":"S021800142052014XBIB035","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1016\/j.neunet.2019.04.025","volume":"116","author":"Sarg\u00fcl M.","year":"2019","journal-title":"Neural Netw."},{"issue":"1","key":"S021800142052014XBIB036","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1109\/JPROC.2015.2494218","volume":"104","author":"Shahriari B.","year":"2016","journal-title":"Proc. IEEE"},{"key":"S021800142052014XBIB038","first-page":"93","volume-title":"Computational Intelligence: Theories, Applications and Future Directions \u2013 Volume II","author":"Soniya","year":"2017"},{"key":"S021800142052014XBIB039","first-page":"1","volume-title":"National System Conf. (NSC) 2017","author":"Soniya","year":"2017"},{"key":"S021800142052014XBIB041","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1145\/3071178.3071229","volume-title":"Proc. Genetic and Evolutionary Computation Conf., GECCO \u201917","author":"Suganuma M.","year":"2017"},{"issue":"8","key":"S021800142052014XBIB043","doi-asserted-by":"crossref","first-page":"2295","DOI":"10.1109\/TNNLS.2018.2881143","volume":"30","author":"Sun Y.","year":"2018","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"S021800142052014XBIB046","doi-asserted-by":"crossref","first-page":"1631","DOI":"10.1007\/s13042-018-0842-5","volume":"10","author":"Wang X.","year":"2019","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"S021800142052014XBIB047","first-page":"1","volume-title":"2018 IEEE Congr. Evolutionary Computation (CEC)","author":"Wang B.","year":"2018"},{"key":"S021800142052014XBIB048","doi-asserted-by":"crossref","first-page":"2476","DOI":"10.1145\/3219819.3219970","volume-title":"Proc. 24th ACM SIGKDD Int. Conf. Knowledge Discovery & Data Mining, KDD \u201918","author":"Wang Y.","year":"2018"},{"key":"S021800142052014XBIB049","doi-asserted-by":"crossref","first-page":"1388","DOI":"10.1109\/ICCV.2017.154","volume-title":"2017 IEEE Int. Conf. Computer Vision (ICCV)","author":"Xie L.","year":"2017"},{"key":"S021800142052014XBIB051","first-page":"2423","volume-title":"IEEE\/CVF Conf. Computer Vision and Pattern Recognition","author":"Zhong Z.","year":"2018"},{"key":"S021800142052014XBIB052","doi-asserted-by":"crossref","first-page":"787","DOI":"10.1016\/j.acha.2019.06.004","volume":"48","author":"Zhou D.-X.","year":"2020","journal-title":"Appl. Comput. Harmon. Anal."},{"key":"S021800142052014XBIB053","first-page":"1","volume-title":"5th Int. Conf. Learning Representations, (ICLR), Conference Track Proceedings","author":"Zoph B.","year":"2017"},{"key":"S021800142052014XBIB054","first-page":"8697","volume-title":"2018 IEEE Conf. Computer Vision and Pattern Recognition (CVPR)","author":"Zoph B.","year":"2018"}],"container-title":["International Journal of Pattern Recognition and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S021800142052014X","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,12,7]],"date-time":"2020-12-07T10:26:15Z","timestamp":1607336775000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/abs\/10.1142\/S021800142052014X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4,30]]},"references-count":37,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2020,12,15]]}},"alternative-id":["10.1142\/S021800142052014X"],"URL":"https:\/\/doi.org\/10.1142\/s021800142052014x","relation":{},"ISSN":["0218-0014","1793-6381"],"issn-type":[{"type":"print","value":"0218-0014"},{"type":"electronic","value":"1793-6381"}],"subject":[],"published":{"date-parts":[[2020,4,30]]}}}