{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T05:48:19Z","timestamp":1775713699100,"version":"3.50.1"},"reference-count":79,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2020,6,12]],"date-time":"2020-06-12T00:00:00Z","timestamp":1591920000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["2019R1A2C1085388"],"award-info":[{"award-number":["2019R1A2C1085388"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Traditional systems of handwriting recognition have relied on handcrafted features and a large amount of prior knowledge. Training an Optical character recognition (OCR) system based on these prerequisites is a challenging task. Research in the handwriting recognition field is focused around deep learning techniques and has achieved breakthrough performance in the last few years. Still, the rapid growth in the amount of handwritten data and the availability of massive processing power demands improvement in recognition accuracy and deserves further investigation. Convolutional neural networks (CNNs) are very effective in perceiving the structure of handwritten characters\/words in ways that help in automatic extraction of distinct features and make CNN the most suitable approach for solving handwriting recognition problems. Our aim in the proposed work is to explore the various design options like number of layers, stride size, receptive field, kernel size, padding and dilution for CNN-based handwritten digit recognition. In addition, we aim to evaluate various SGD optimization algorithms in improving the performance of handwritten digit recognition. A network\u2019s recognition accuracy increases by incorporating ensemble architecture. Here, our objective is to achieve comparable accuracy by using a pure CNN architecture without ensemble architecture, as ensemble architectures introduce increased computational cost and high testing complexity. Thus, a CNN architecture is proposed in order to achieve accuracy even better than that of ensemble architectures, along with reduced operational complexity and cost. Moreover, we also present an appropriate combination of learning parameters in designing a CNN that leads us to reach a new absolute record in classifying MNIST handwritten digits. We carried out extensive experiments and achieved a recognition accuracy of 99.87% for a MNIST dataset.<\/jats:p>","DOI":"10.3390\/s20123344","type":"journal-article","created":{"date-parts":[[2020,6,15]],"date-time":"2020-06-15T05:56:27Z","timestamp":1592200587000},"page":"3344","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":228,"title":["Improved Handwritten Digit Recognition Using Convolutional Neural Networks (CNN)"],"prefix":"10.3390","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1191-9173","authenticated-orcid":false,"given":"Savita","family":"Ahlawat","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Maharaja Surajmal Institute of Technology, New Delhi 110058, India"}]},{"given":"Amit","family":"Choudhary","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Maharaja Surajmal Institute, New Delhi 110058, India"}]},{"given":"Anand","family":"Nayyar","sequence":"additional","affiliation":[{"name":"Graduate School, Duy Tan University, Da Nang 550000, Vietnam"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1118-9569","authenticated-orcid":false,"given":"Saurabh","family":"Singh","sequence":"additional","affiliation":[{"name":"Department of Industrial &amp; Systems Engineering, Dongguk University, Seoul 04620, Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1110-4011","authenticated-orcid":false,"given":"Byungun","family":"Yoon","sequence":"additional","affiliation":[{"name":"Department of Industrial &amp; Systems Engineering, Dongguk University, Seoul 04620, Korea"}]}],"member":"1968","published-online":{"date-parts":[[2020,6,12]]},"reference":[{"key":"ref_1","unstructured":"Dalal, N., and Triggs, B. (2005, January 20\u201326). Histograms of oriented gradients for human detection. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR \u201905), San Diego, CA, USA."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1023\/B:VISI.0000029664.99615.94","article-title":"Distinctive image features from scale-invariant keypoints","volume":"60","author":"Lowe","year":"2004","journal-title":"Int. J. Comput. Vis."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1142\/S021962201841002X","article-title":"A new approach for stock price analysis and prediction based on SSA and SVM","volume":"18","author":"Xiao","year":"2019","journal-title":"Int. J. Inf. Technol. Decis. Making"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"3815","DOI":"10.1109\/TNNLS.2017.2741349","article-title":"Dissipativity and synchronization of generalized BAM neural networks with multivariate discontinuous activations","volume":"29","author":"Wang","year":"2017","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1187","DOI":"10.1007\/s00500-014-1332-7","article-title":"A novel SVM by combining kernel principal component analysis and improved chaotic particle swarm optimization for intrusion detection","volume":"19","author":"Kuang","year":"2015","journal-title":"Soft Comput."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Choudhary, A., Ahlawat, S., and Rishi, R. (2014, January 6\u20139). A binarization feature extraction approach to OCR: MLP vs. RBF. Proceedings of the International Conference on Distributed Computing and Technology ICDCIT, Bhubaneswar, India.","DOI":"10.1007\/978-3-319-04483-5_35"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1007\/BF00344251","article-title":"Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position","volume":"36","author":"Fukushima","year":"1980","journal-title":"Biol. Cybern."},{"key":"ref_8","unstructured":"Jarrett, K., Kavukcuoglu, K., Ranzato, M., and LeCun, Y. (October, January 29). What is the best multi-stage architecture for object recognition. Proceedings of the IEEE 12th International Conference on Computer Vision (ICCV), Kyoto, Japam."},{"key":"ref_9","unstructured":"Ciresan, D.C., Meier, U., Masci, J., Gambardella, L.M., and Schmidhuber, J. (2011). High-performance neural networks for visual object classification. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Ciresan, D.C., Meier, U., and Schmidhuber, J. (2012). Multi-column deep neural networks for image classification. arXiv.","DOI":"10.1109\/CVPR.2012.6248110"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1318","DOI":"10.1016\/j.patcog.2011.09.021","article-title":"A novel hybrid CNN\u2013SVM classifier for recognizing handwritten digits","volume":"45","author":"Niu","year":"2012","journal-title":"Pattern Recognit."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1016\/j.patrec.2018.04.001","article-title":"Data augmentation and directional feature maps extraction for in-air handwritten Chinese character recognition based on convolutional neural network","volume":"111","author":"Qu","year":"2018","journal-title":"Pattern Recognit. Lett."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/j.inffus.2017.03.008","article-title":"On building ensembles of stacked denoising auto-encoding classifiers and their further improvement","volume":"39","year":"2018","journal-title":"Inf. Fusion"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2206","DOI":"10.1016\/j.patrec.2005.03.028","article-title":"Cost-conscious classifier ensembles","volume":"26","author":"Demir","year":"2005","journal-title":"Pattern Recognit. Lett."},{"key":"ref_15","first-page":"745","article-title":"A neural approach to cursive handwritten character recognition using features extracted from binarization technique","volume":"319","author":"Choudhary","year":"2015","journal-title":"Complex Syst. Model. Control Intell. Soft Comput."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Choudhary, A., Rishi, R., and Ahlawat, S. (2011, January 2\u20134). Handwritten numeral recognition using modified BP ANN structure. Proceedings of the Communication in Computer and Information Sciences (CCIS-133), Advanced Computing, CCSIT 2011, Royal Orchid Central, Bangalore, India.","DOI":"10.1007\/978-3-642-17881-8_6"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1683","DOI":"10.1007\/s13042-017-0673-9","article-title":"Finite-time synchronization by switching state-feedback control for discontinuous Cohen\u2013Grossberg neural networks with mixed delays","volume":"9","author":"Cai","year":"2018","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"ref_18","first-page":"121","article-title":"Adversarial learning for distant supervised relation extraction","volume":"55","author":"Zeng","year":"2018","journal-title":"Comput. Mater. Contin."},{"key":"ref_19","first-page":"493","article-title":"Detecting iris liveness with batch normalized convolutional neural network","volume":"58","author":"Long","year":"2019","journal-title":"Comput. Mater. Contin."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1016\/j.neucom.2018.09.065","article-title":"New studies on dynamic analysis of inertial neural networks involving non-reduced order method","volume":"325","author":"Chuangxia","year":"2019","journal-title":"Neurocomputing"},{"key":"ref_21","first-page":"541","article-title":"Reversible natural language watermarking using synonym substitution and arithmetic coding","volume":"55","author":"Xiang","year":"2018","journal-title":"Comput. Mater. Contin."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1016\/j.ins.2014.02.132","article-title":"Decentralized adaptive fuzzy control for a class of large-scale MIMO nonlinear systems with strong interconnection and its application to automated highway systems","volume":"274","author":"Huang","year":"2014","journal-title":"Inf. Sci."},{"key":"ref_23","first-page":"85","article-title":"Improving the character recognition efficiency of feed forward bp neural network","volume":"3","author":"Choudhary","year":"2011","journal-title":"Int. J. Comput. Sci. Inf. Technol."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"304","DOI":"10.2174\/2213275911666181120111342","article-title":"A genetic algorithm based feature selection for handwritten digit recognition","volume":"12","author":"Ahlawat","year":"2019","journal-title":"Recent Pat. Comput. Sci."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","article-title":"A fast learning algorithm for deep belief nets","volume":"18","author":"Hinton","year":"2006","journal-title":"Neural Comput."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Pham, V., Bluche, T., Kermorvant, C., and Louradour, J. (2014, January 1\u20134). Dropout improves recurrent neural networks for handwriting recognition. Proceedings of the 14th Int. Conf. on Frontiers in Handwriting Recognition, Heraklion, Greece.","DOI":"10.1109\/ICFHR.2014.55"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1016\/j.inffus.2020.04.002","article-title":"MNIST-NET10: A heterogeneous deep networks fusion based on the degree of certainty to reach 0.1% error rate","volume":"62","author":"Tabik","year":"2020","journal-title":"Ensembles Overv. Proposal Inf. Fusion"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1007\/s13042-014-0315-4","article-title":"Incremental approaches to knowledge reduction based on characteristic matrices","volume":"8","author":"Lang","year":"2017","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"SegNet: A Deep convolutional encoder-decoder architecture for image segmentation","volume":"39","author":"Badrinarayanan","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_30","first-page":"1510","article-title":"PPNC: Privacy preserving scheme for random linear network coding in smart grid","volume":"11","author":"He","year":"2017","journal-title":"KSII Trans. Internet Inf. Syst."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/j.neucom.2018.02.008","article-title":"Offline continuous handwriting recognition using sequence to sequence neural networks","volume":"289","author":"Sueiras","year":"2018","journal-title":"Neurocomputing."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1016\/j.patrec.2017.05.019","article-title":"A new image classification method based on modified condensed nearest neighbor and convolutional neural networks","volume":"94","author":"Liang","year":"2017","journal-title":"Pattern Recognit. Lett."},{"key":"ref_33","unstructured":"Simard, P.Y., Steinkraus, D., and Platt, J.C. (2003, January 3\u20136). Best practice for convolutional neural networks applied to visual document analysis. Proceedings of the Seventh International Conference on Document Analysis and Recognition (ICDAR 2003), Edinburgh, UK."},{"key":"ref_34","unstructured":"Wang, T., Wu, D.J., Coates, A., and Ng, A.Y. (2012, January 11\u201315). End-to-end text recognition with convolutional neural networks. Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012), Tsukuba, Japan."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","article-title":"An End-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition","volume":"39","author":"Shi","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., and Darrell, T. (2015, January 7\u201312). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs","volume":"40","author":"Chen","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Noh, H., Hong, S., and Han, B. (2015, January 11\u201318). Learning deconvolution network for semantic segmentation. Proceedings of the IEEE International Conference on Computer Vision, Araucano Park, Las Condes, Chille.","DOI":"10.1109\/ICCV.2015.178"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1016\/j.cogsys.2017.11.002","article-title":"Investigation on deep learning for off-line handwritten Arabic character recognition","volume":"50","author":"Boufenar","year":"2018","journal-title":"Cogn. Syst. Res."},{"key":"ref_40","unstructured":"Kavitha, B., and Srimathi, C. (2019). Benchmarking on offline Handwritten Tamil Character Recognition using convolutional neural networks. J. King Saud Univ. Comput. Inf. Sci."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Dewan, S., and Chakravarthy, S. (2012, January 12\u201315). A system for offline character recognition using auto-encoder networks. Proceedings of the International Conference on Neural Information Processing, Doha, Qatar.","DOI":"10.1007\/978-3-642-34478-7_12"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1143","DOI":"10.1007\/s00521-017-3146-x","article-title":"Handwritten Urdu character recognition using one-dimensional BLSTM classifier","volume":"31","author":"Ahmed","year":"2019","journal-title":"Neural Comput. Appl."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Husnain, M., Saad Missen, M., Mumtaz, S., Jhanidr, M.Z., Coustaty, M., Luqman, M.M., Ogier, J.-M., and Choi, G.S. (2019). Recognition of urdu handwritten characters using convolutional neural network. Appl. Sci., 9.","DOI":"10.3390\/app9132758"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1016\/j.patcog.2017.05.022","article-title":"A multi-scale deep quad tree based feature extraction method for the recognition of isolated handwritten characters of popular indic scripts","volume":"71","author":"Sarkhel","year":"2017","journal-title":"Pattern Recognit."},{"key":"ref_45","unstructured":"Xie, Z., Sun, Z., Jin, L., Feng, Z., and Zhang, S. (2016, January 4\u20138). Fully convolutional recurrent network for handwritten chinese text recognition. Proceedings of the 23rd International Conference on Pattern Recognition (ICPR 2016), Cancun, Mexico."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1016\/j.patcog.2012.06.021","article-title":"Online and offline handwritten Chinese character recognition: Benchmarking on new databases","volume":"46","author":"Liu","year":"2013","journal-title":"Pattern Recognit."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/j.patcog.2016.12.026","article-title":"Improving handwritten chinese text recognition using neural network language models and convolutional neural network shape models","volume":"65","author":"Wu","year":"2017","journal-title":"Pattern Recognit."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1016\/j.patrec.2019.09.019","article-title":"Multiobjective optimization for recognition of isolated handwritten Indic scripts","volume":"128","author":"Gupta","year":"2019","journal-title":"Pattern Recognit. Lett."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Nguyen, C.T., Khuong, V.T.M., Nguyen, H.T., and Nakagawa, M. (2019). CNN based spatial classification features for clustering offline handwritten mathematical expressions. Pattern Recognit. Lett.","DOI":"10.1016\/j.patrec.2019.12.015"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.patrec.2020.02.016","article-title":"Text alignment in early printed books combining deep learning and dynamic programming","volume":"133","author":"Ziran","year":"2020","journal-title":"Pattern Recognit. Lett."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"604","DOI":"10.1016\/j.patcog.2018.12.017","article-title":"Intelligent character recognition using fully convolutional neural networks","volume":"88","author":"Ptucha","year":"2019","journal-title":"Pattern Recognit."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"828","DOI":"10.1016\/j.patrec.2019.02.009","article-title":"A new hyperparameters optimization method for convolutional neural networks","volume":"125","author":"Cui","year":"2019","journal-title":"Pattern Recognit. Lett."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"106902","DOI":"10.1016\/j.compchemeng.2020.106902","article-title":"HY-POP: Hyperparameter optimization of machine learning models through parametric programming","volume":"139","author":"Tso","year":"2020","journal-title":"Comput. Chem. Eng."},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (July, January 26). Deep residual learning for image recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_55","unstructured":"Christian, S., Wei, L., Yangqing, J., Pierre, S., Scott, R., Dragomir, A., and Andrew, R. (2015, January 7\u201312). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA."},{"key":"ref_56","unstructured":"Simonyan, K., and Zisserman, A. (2015, January 7\u20139). Very deep convolutional networks for large-scale image recognition. Proceedings of the International Conference on Learning Representations, San Diego, CA, USA."},{"key":"ref_57","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1016\/j.neuroimage.2016.10.001","article-title":"Seeing it all: Convolutional network layers map the function of the human visual system","volume":"152","author":"Eickenberg","year":"2017","journal-title":"NeuroImage"},{"key":"ref_59","unstructured":"Le, H., and Borji, A. (2018). What are the receptive, effective receptive, and projective fields of neurons in convolutional neural networks?. arXiv."},{"key":"ref_60","unstructured":"Luo, W., Li, Y., Urtasun, R., and Zemel, R. (2017). Understanding the effective receptive field in deep convolutional neural networks. arXiv."},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"1219","DOI":"10.1016\/j.neucom.2017.09.062","article-title":"Image super-resolution using a dilated convolutional neural network","volume":"275","author":"Lin","year":"2018","journal-title":"Neurocomputing"},{"key":"ref_62","doi-asserted-by":"crossref","unstructured":"Scherer, D., Muller, A., and Behnke, S. (2010, January 15\u201318). Evaluation of pooling operations in convolutional architectures for object recognition. Proceedings of the International Conference on Artificial Neural Networks, Thessaloniki, Greece.","DOI":"10.1007\/978-3-642-15825-4_10"},{"key":"ref_63","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/j.neunet.2016.07.003","article-title":"Rank-based pooling for deep convolutional neural networks","volume":"83","author":"Shi","year":"2016","journal-title":"Neural Netw."},{"key":"ref_64","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.neunet.2015.07.007","article-title":"Towards dropout training for convolutional neural networks","volume":"71","author":"Wu","year":"2015","journal-title":"Neural Netw."},{"key":"ref_65","unstructured":"Saeed, F., Paul, A., Karthigaikumar, P., and Nayyar, A. (2019). Convolutional neural network based early fire detection. Multimed. Tools Appl., 1\u201317."},{"key":"ref_66","doi-asserted-by":"crossref","first-page":"012012","DOI":"10.1088\/1742-6596\/1142\/1\/012012","article-title":"Machine learning from theory to algorithms: An overview","volume":"1142","author":"Alzubi","year":"2018","journal-title":"J. Phys. Conf. Series"},{"key":"ref_67","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"Duchi","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_68","unstructured":"Zeiler, M.D. (2012). ADADELTA: An Adaptive Learning Rate Method. arXiv."},{"key":"ref_69","unstructured":"Kingma, D., and Ba, J. (2015, January 7\u20139). Adam: A method for stochastic optimization. Proceedings of the International Conference on Learning Representations, San Diego, CA, USA."},{"key":"ref_70","unstructured":"Bartlett, P., Hazan, E., and Rakhlin, A. (2008, January 8\u201311). Adaptive online gradient descent. Proceedings of the NIPS, Vancuver, BC, Canada."},{"key":"ref_71","doi-asserted-by":"crossref","unstructured":"Do, C.B., Le, Q.V., and Foo, C.S. (2009, January 14\u201318). Proximal regularization for online and batch learning. Proceedings of the ICML, Montreal, QC, Canada.","DOI":"10.1145\/1553374.1553407"},{"key":"ref_72","doi-asserted-by":"crossref","unstructured":"Hinton, G.E., and Salakhutdinov, R.R. (2006). Reducing the dimensionality of data with neural networks. Science.","DOI":"10.1126\/science.1127647"},{"key":"ref_73","doi-asserted-by":"crossref","unstructured":"Shalev-Shwartz, S., Singer, Y., and Srebro, N. (2007, January 20\u201324). Pegasos: Primal estimated sub-gradient solver for svm. Proceedings of the ICML, Corvallis, OR, USA.","DOI":"10.1145\/1273496.1273598"},{"key":"ref_74","first-page":"2595","article-title":"Parallelized stochastic gradient descent","volume":"2","author":"Zinkevich","year":"2010","journal-title":"NIPS"},{"key":"ref_75","doi-asserted-by":"crossref","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","article-title":"Backpropagation applied to handwritten zip code recognition","volume":"1","author":"LeCun","year":"1989","journal-title":"Neural Comput."},{"key":"ref_76","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1613\/jair.105","article-title":"Solving multiclass learning problems via error-correcting output codes","volume":"1","author":"Dietterich","year":"1995","journal-title":"J. Artif. Intell. Res."},{"key":"ref_77","unstructured":"Wan, L., Zeiler, M., Zhang, S., Le Cun, Y., and Fergus, R. (2013, January 16\u201321). Regularization of neural networks using DropConnect. Proceedings of the 30th International Conference on Machine Learning (PMLR), Atlanta, GA, USA."},{"key":"ref_78","unstructured":"Loquercio, A., Della Torre, A., and Buscema, M. (2017). Computational Eco-Systems for handwritten digits recognition. arXiv."},{"key":"ref_79","doi-asserted-by":"crossref","unstructured":"Soomro, M., Farooq, M.A., and Raza, M.A. (2017, January 18\u201320). Performance evaluation of advanced deep learning architectures for offline handwritten character recognition. Proceedings of the International Conference on Frontiers of Information Technology (FIT), Islamabad, Pakistan.","DOI":"10.1109\/FIT.2017.00071"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/12\/3344\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T09:38:31Z","timestamp":1760175511000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/12\/3344"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,12]]},"references-count":79,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2020,6]]}},"alternative-id":["s20123344"],"URL":"https:\/\/doi.org\/10.3390\/s20123344","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,6,12]]}}}