{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:35:48Z","timestamp":1742913348437,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789811978661"},{"type":"electronic","value":"9789811978678"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-981-19-7867-8_5","type":"book-chapter","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T12:02:18Z","timestamp":1683288138000},"page":"51-63","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Moment Centralization-Based Gradient Descent Optimizers for\u00a0Convolutional Neural Networks"],"prefix":"10.1007","author":[{"given":"Sumanth","family":"Sadu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiv Ram","family":"Dubey","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S. R.","family":"Sreeja","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,5,6]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Basha, S.S., Ghosh, S., Babu, K.K., Dubey, S.R., Pulabaigari, V., Mukherjee, S.: Rccnet: An efficient convolutional neural network for histological routine colon cancer nuclei classification. In: 2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV). pp. 1222\u20131227. IEEE (2018)","DOI":"10.1109\/ICARCV.2018.8581147"},{"key":"5_CR2","unstructured":"Bernstein, J., Wang, Y.X., Azizzadenesheli, K., Anandkumar, A.: signsgd: Compressed optimisation for non-convex problems. In: International Conference on Machine Learning. pp. 560\u2013569 (2018)"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Bottou, L.: Large-scale machine learning with stochastic gradient descent. In: Proceedings of the COMPSTAT, pp. 177\u2013186 (2010)","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"5_CR4","unstructured":"Chen, Z., Badrinarayanan, V., Lee, C.Y., Rabinovich, A.: Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks. In: International Conference on Machine Learning. pp. 794\u2013803. PMLR (2018)"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Choi, S., Kim, T., Jeong, M., Park, H., Kim, C.: Meta batch-instance normalization for generalizable person re-identification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 3425\u20133435 (2021)","DOI":"10.1109\/CVPR46437.2021.00343"},{"issue":"11","key":"5_CR6","doi-asserted-by":"publisher","first-page":"4500","DOI":"10.1109\/TNNLS.2019.2955777","volume":"31","author":"SR Dubey","year":"2019","unstructured":"Dubey, S.R., Chakraborty, S., Roy, S.K., Mukherjee, S., Singh, S.K., Chaudhuri, B.B.: diffgrad: an optimization method for convolutional neural networks. IEEE transactions on neural networks and learning systems 31(11), 4500\u20134511 (2019)","journal-title":"IEEE transactions on neural networks and learning systems"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Dubey, S., Basha, S., Singh, S., Chaudhuri, B.: Curvature injected adaptive momentum optimizer for convolutional neural networks. arXiv preprint arXiv:2109.12504 (2021)","DOI":"10.1109\/TAI.2022.3208223"},{"key":"5_CR8","unstructured":"Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 12(Jul), 2121\u20132159 (2011)"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"5_CR10","unstructured":"Hinton, G., Srivastava, N., Swersky, K.: Neural networks for machine learning. Lecture 6a overview of mini-batch gradient descent course (2012)"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Huang, H., Wang, C., Dong, B.: Nostalgic adam: Weighting more of the past gradients when designing the adaptive learning rate. In: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence. pp. 2556\u20132562 (2019)","DOI":"10.24963\/ijcai.2019\/355"},{"key":"5_CR12","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning. pp. 448\u2013456. PMLR (2015)"},{"key":"5_CR13","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. In: International Conference on Learning Representations (2015)"},{"key":"5_CR14","unstructured":"Krizhevsky, A., Hinton, G., et\u00a0al.: Learning multiple layers of features from tiny images. Tech Report (2009)"},{"key":"5_CR15","first-page":"1097","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25, 1097\u20131105 (2012)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"5_CR16","unstructured":"Le, Y., Yang, X.: Tiny imagenet visual recognition challenge. CS 231N 7(7), 3 (2015)"},{"issue":"7553","key":"5_CR17","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436\u2013444 (2015)","journal-title":"Nature"},{"key":"5_CR18","unstructured":"Liu, L., Jiang, H., He, P., Chen, W., Liu, X., Gao, J., Han, J.: On the variance of the adaptive learning rate and beyond. In: International Conference on Learning Representations (2019)"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Repala, V.K., Dubey, S.R.: Dual cnn models for unsupervised monocular depth estimation. In: International Conference on Pattern Recognition and Machine Intelligence. pp. 209\u2013217. Springer (2019)","DOI":"10.1007\/978-3-030-34869-4_23"},{"key":"5_CR20","unstructured":"Roy, S., Paoletti, M., Haut, J., Dubey, S., Kar, P., Plaza, A., Chaudhuri, B.: Angulargrad: A new optimization technique for angular convergence of convolutional neural networks. arXiv preprint arXiv:2105.10190 (2021)"},{"key":"5_CR21","first-page":"901","volume":"29","author":"T Salimans","year":"2016","unstructured":"Salimans, T., Kingma, D.P.: Weight normalization: a simple reparameterization to accelerate training of deep neural networks. Adv. Neural Inf. Process. Syst. 29, 901\u2013909 (2016)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"5_CR22","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2015)"},{"key":"5_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2019.105524","volume":"97","author":"D Singh","year":"2020","unstructured":"Singh, D., Singh, B.: Investigating the impact of data normalization on classification performance. Appl. Soft Comput. 97, 105524 (2020)","journal-title":"Appl. Soft Comput."},{"key":"5_CR24","doi-asserted-by":"crossref","unstructured":"Srivastava, Y., Murali, V., Dubey, S.R.: Hard-mining loss based convolutional neural network for face recognition. In: International Conference on Computer Vision and Image Processing. pp. 70\u201380. Springer (2020)","DOI":"10.1007\/978-981-16-1103-2_7"},{"key":"5_CR25","unstructured":"Sutskever, I., Martens, J., Dahl, G., Hinton, G.: On the importance of initialization and momentum in deep learning. In: Proceedings of the International Conference on Machine Learning. pp. 1139\u20131147 (2013)"},{"key":"5_CR26","doi-asserted-by":"crossref","unstructured":"Yong, H., Huang, J., Hua, X., Zhang, L.: Gradient centralization: a new optimization technique for deep neural networks. In: European Conference on Computer Vision. pp. 635\u2013652. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_37"},{"key":"5_CR27","unstructured":"Zhuang, J., Tang, T., Ding, Y., Tatikonda, S.C., Dvornek, N., Papademetris, X., Duncan, J.: Adabelief optimizer: Adapting stepsizes by the belief in observed gradients. Adv. Neural Inf. Process. Syst. 33 (2020)"}],"container-title":["Lecture Notes in Networks and Systems","Computer Vision and Machine Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-19-7867-8_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T21:36:28Z","timestamp":1729373788000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-19-7867-8_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789811978661","9789811978678"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-19-7867-8_5","relation":{},"ISSN":["2367-3370","2367-3389"],"issn-type":[{"type":"print","value":"2367-3370"},{"type":"electronic","value":"2367-3389"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"6 May 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}