{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T16:04:18Z","timestamp":1775145858824,"version":"3.50.1"},"reference-count":57,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T00:00:00Z","timestamp":1709164800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T00:00:00Z","timestamp":1709164800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Project supported by the national natural science foundation of China","award":["62166005"],"award-info":[{"award-number":["62166005"]}]},{"DOI":"10.13039\/501100018555","name":"Science and Technology Program of Guizhou Province","doi-asserted-by":"publisher","award":["QKH-ZK[2022]130"],"award-info":[{"award-number":["QKH-ZK[2022]130"]}],"id":[{"id":"10.13039\/501100018555","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018555","name":"Science and Technology Program of Guizhou Province","doi-asserted-by":"publisher","award":["QKH[2021]335"],"award-info":[{"award-number":["QKH[2021]335"]}],"id":[{"id":"10.13039\/501100018555","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018555","name":"Science and Technology Program of Guizhou Province","doi-asserted-by":"publisher","award":["QKHZC[2022]003"],"award-info":[{"award-number":["QKHZC[2022]003"]}],"id":[{"id":"10.13039\/501100018555","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Developing objects and projects of scientific and technological talents in Guiyang city","award":["No.ZKHT[2023]48-8"],"award-info":[{"award-number":["No.ZKHT[2023]48-8"]}]},{"name":"Joint Open Fund Project of Key Laboratories of the Ministry of Education","award":["[2020]248"],"award-info":[{"award-number":["[2020]248"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2024,6]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Catastrophic forgetting in neural networks is a common problem, in which neural networks lose information from previous tasks after training on new tasks. Although adopting a regularization method that preferentially retains the parameters important to the previous task to avoid catastrophic forgetting has a positive effect; existing regularization methods cause the gradient to be near zero because the loss is at the local minimum. To solve this problem, we propose a new continuous learning method with Bayesian parameter updating and weight memory (CL-BPUWM). First, a parameter updating method based on the Bayes criterion is proposed to allow the neural network to gradually obtain new knowledge. The diagonal of the Fisher information matrix is then introduced to significantly minimize computation and increase parameter updating efficiency. Second, we suggest calculating the importance weight by observing how changes in each network parameter affect the model prediction output. In the process of model parameter updating, the Fisher information matrix and the sensitivity of the network are used as the quadratic penalty terms of the loss function. Finally, we apply dropout regularization to reduce model overfitting during training and to improve model generalizability. CL-BPUWM performs very well in continuous learning for classification tasks on CIFAR-100 dataset, CIFAR-10 dataset, and MNIST dataset. On CIFAR-100 dataset, it is 0.8%, 1.03% and 0.75% higher than the best performing regularization method (EWC) in three task partitions. On CIFAR-10 dataset, it is 2.25% higher than the regularization method (EWC) and 0.7% higher than the scaled method (GR). It is 0.66% higher than the regularization method (EWC) on the MNIST dataset. When the CL-BPUWM method was combined with the brain-inspired replay model under the CIFAR-100 and CIFAR-10 datasets, the classification accuracy was 2.35% and 5.38% higher than that of the baseline method, BI-R\u2009+\u2009SI.<\/jats:p>","DOI":"10.1007\/s40747-024-01350-1","type":"journal-article","created":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T10:02:33Z","timestamp":1709200953000},"page":"3891-3906","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["CL-BPUWM: continuous learning with Bayesian parameter updating and weight memory"],"prefix":"10.1007","volume":"10","author":[{"given":"Yao","family":"He","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1915-9487","authenticated-orcid":false,"given":"Jing","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Shaobo","family":"Li","sequence":"additional","affiliation":[]},{"given":"Jianjun","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Yaping","family":"Ren","sequence":"additional","affiliation":[]},{"given":"Qing","family":"Ji","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,2,29]]},"reference":[{"key":"1350_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11063-023-11189-1","volume":"10","author":"X Song","year":"2023","unstructured":"Song X, Wu N, Song S et al (2023) Switching-like event-triggered state estimation for reaction-diffusion neural networks against DoS attacks. Neural Process Lett 10:1\u201322. https:\/\/doi.org\/10.1007\/s11063-023-11189-1","journal-title":"Neural Process Lett"},{"key":"1350_CR2","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-023-01135-y","author":"Z Peng","year":"2023","unstructured":"Peng Z, Song X, Song S et al (2023) Hysteresis quantified control for switched reaction\u2013diffusion systems and its application. Complex Intell Syst. https:\/\/doi.org\/10.1007\/s40747-023-01135-y","journal-title":"Complex Intell Syst"},{"key":"1350_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126498","volume":"550","author":"X Song","year":"2023","unstructured":"Song X, Wu N, Song S et al (2023) Bipartite synchronization for cooperative-competitive neural networks with reaction\u2013diffusion terms via dual event-triggered mechanism. Neurocomputing 550:126498. https:\/\/doi.org\/10.1016\/j.neucom.2023.126498","journal-title":"Neurocomputing"},{"key":"1350_CR4","doi-asserted-by":"publisher","unstructured":"Gong X, Xia X, Zhu W, et al (2021) Deformable Gabor feature networks for biomedical image classification. In: Proceedings of the IEEE\/CVF Winter Conference on applications of computer vision, pp 4004\u20134012. https:\/\/doi.org\/10.1109\/wacv48630.2021.00405","DOI":"10.1109\/wacv48630.2021.00405"},{"issue":"3","key":"1350_CR5","doi-asserted-by":"publisher","first-page":"1656","DOI":"10.1109\/JSEN.2019.2947994","volume":"20","author":"H Shih","year":"2019","unstructured":"Shih H, Cheng H, Fu J (2019) Image classification using synchronized rotation local ternary pattern. IEEE Sens J 20(3):1656\u20131663. https:\/\/doi.org\/10.1109\/JSEN.2019.2947994","journal-title":"IEEE Sens J"},{"key":"1350_CR6","doi-asserted-by":"publisher","first-page":"7549","DOI":"10.1109\/TIP.2020.3004249","volume":"29","author":"Q Wang","year":"2020","unstructured":"Wang Q, Liu X, Liu W et al (2020) Metasearch: incremental product search via deep meta-learning. IEEE Trans Image Process 29:7549\u20137564. https:\/\/doi.org\/10.1109\/TIP.2020.3004249","journal-title":"IEEE Trans Image Process"},{"key":"1350_CR7","doi-asserted-by":"publisher","unstructured":"Chen P, Yu X, Han X, et al (2022) Point-to-box network for accurate object detection via single point supervision. In: European Conference on computer vision. Springer, pp 51\u201367. https:\/\/doi.org\/10.1007\/978-3-031-20077-9_4","DOI":"10.1007\/978-3-031-20077-9_4"},{"key":"1350_CR8","doi-asserted-by":"publisher","unstructured":"Sheng H, Cai S, Zhao N, et al (2022) Rethinking IoU-based optimization for single-stage 3D object detection. In: European Conference on computer vision. Springer, pp 544\u2013561. https:\/\/doi.org\/10.1007\/978-3-031-20077-9_32","DOI":"10.1007\/978-3-031-20077-9_32"},{"key":"1350_CR9","doi-asserted-by":"publisher","unstructured":"Zhong X, Ding C, Li Z, et al (2022) Towards hard-positive query mining for DETR-based human-object interaction detection. In: European Conference on computer vision. Springer, pp 444\u2013460. https:\/\/doi.org\/10.1109\/10.1007\/978-3-031-19812-0_26","DOI":"10.1109\/10.1007\/978-3-031-19812-0_26"},{"issue":"4","key":"1350_CR10","doi-asserted-by":"publisher","first-page":"45406","DOI":"10.1088\/1361-6501\/acb075","volume":"34","author":"L Shen","year":"2023","unstructured":"Shen L, Tao H, Ni Y et al (2023) Improved YOLOv3 model with feature map cropping for multi-scale road object detection. Meas Sci Technol 34(4):45406. https:\/\/doi.org\/10.1088\/1361-6501\/acb075","journal-title":"Meas Sci Technol"},{"key":"1350_CR11","doi-asserted-by":"publisher","unstructured":"He J, Deng Z, Zhou L, et al (2019) Adaptive pyramid context network for semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, pp 7519\u20137528. https:\/\/doi.org\/10.1109\/CVPR.2019.00770","DOI":"10.1109\/CVPR.2019.00770"},{"key":"1350_CR12","doi-asserted-by":"publisher","unstructured":"Fu J, Liu J, Tian H, et al (2019) Dual attention network for scene segmentation. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, pp 3146\u20133154. https:\/\/doi.org\/10.1109\/cvpr.2019.00326","DOI":"10.1109\/cvpr.2019.00326"},{"key":"1350_CR13","first-page":"2994","volume":"30","author":"H Shin","year":"2017","unstructured":"Shin H, Lee JK, Kim J et al (2017) Continual learning with deep generative replay. Adv Neural Inf Process Syst 30:2994\u20133003","journal-title":"Adv Neural Inf Process Syst"},{"key":"1350_CR14","unstructured":"Aljundi R, Lin M, Goujaud B, et al (2019) Online continual learning with no task boundaries. 3 arXiv preprint arXiv:1903.08671"},{"key":"1350_CR15","doi-asserted-by":"publisher","unstructured":"Chaudhry A, Rohrbach M, Elhoseiny M et al (2019) Continual learning with tiny episodic memories. Mach Learn. https:\/\/doi.org\/10.48550\/arXiv.1902.10486.","DOI":"10.48550\/arXiv.1902.10486."},{"key":"1350_CR16","doi-asserted-by":"publisher","unstructured":"De Lange M, Tuytelaars T (2021) Continual prototype evolution: Learning online from non-stationary data streams. In: Proceedings of the IEEE\/CVF International Conference on computer vision. ELECTR NETWORK, pp 8250\u20138259. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00814","DOI":"10.1109\/ICCV48922.2021.00814"},{"issue":"7","key":"1350_CR17","doi-asserted-by":"publisher","first-page":"3366","DOI":"10.1109\/TPAMI.2021.3057446","volume":"44","author":"M De Lange","year":"2021","unstructured":"De Lange M, Aljundi R, Masana M et al (2021) A continual learning survey: Defying forgetting in classification tasks. IEEE Trans Pattern Anal Mach Intell 44(7):3366\u20133385. https:\/\/doi.org\/10.1109\/TPAMI.2021.3057446","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"6","key":"1350_CR18","doi-asserted-by":"publisher","first-page":"3461","DOI":"10.1109\/TSMC.2022.3225381","volume":"53","author":"Z Zhuang","year":"2023","unstructured":"Zhuang Z, Tao H, Chen Y et al (2023) An optimal iterative learning control approach for linear systems with nonuniform trial lengths under input constraints. IEEE Trans Syst Man Cybern Syst 53(6):3461\u20133473. https:\/\/doi.org\/10.1109\/TSMC.2022.3225381","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"key":"1350_CR19","unstructured":"Goodfellow I J, Mirza M, Xiao D, et al (2013) An empirical investigation of catastrophic forgetting in gradient-based neural networks. arXiv preprint arXiv:1312.6211"},{"key":"1350_CR20","doi-asserted-by":"publisher","unstructured":"Castro FM, Mar\u00edn-Jim\u00e9nez MJ, Guil N, et al (2018) End-to-end incremental learning. In: Proceedings of the European Conference on computer vision (ECCV), pp 233\u2013248. https:\/\/doi.org\/10.1007\/978-3-030-01258-8_15","DOI":"10.1007\/978-3-030-01258-8_15"},{"key":"1350_CR21","doi-asserted-by":"publisher","unstructured":"Douillard A, Cord M, Ollion C, et al (2020) Podnet: Pooled outputs distillation for small-tasks incremental learning. In: European Conference on computer vision. Springer, pp 86\u2013102. https:\/\/doi.org\/10.1007\/978-3-030-58565-5_6","DOI":"10.1007\/978-3-030-58565-5_6"},{"key":"1350_CR22","doi-asserted-by":"publisher","unstructured":"Rebuffi S, Kolesnikov A, Sperl G, et al (2017) icarl: Incremental classifier and representation learning. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 2001\u20132010. https:\/\/doi.org\/10.1109\/cvpr.2017.587","DOI":"10.1109\/cvpr.2017.587"},{"key":"1350_CR23","doi-asserted-by":"publisher","unstructured":"Wu Y, Chen Y, Wang L, et al (2019) Large scale incremental learning. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition. Long Beach, CA, pp 374\u2013382. https:\/\/doi.org\/10.1109\/CVPR.2019.00046","DOI":"10.1109\/CVPR.2019.00046"},{"key":"1350_CR24","doi-asserted-by":"publisher","unstructured":"Bang J, Kim H, Yoo Y, et al (2021) Rainbow memory: Continual learning with a memory of diverse samples. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition. Nashville, TN, USA, pp 8218\u20138227. https:\/\/doi.org\/10.1109\/CVPR46437.2021.00812","DOI":"10.1109\/CVPR46437.2021.00812"},{"key":"1350_CR25","unstructured":"Chaudhry A, Rohrbach M, Elhoseiny M, et al (2019) On tiny episodic memories in continual learning. arXiv preprint arXiv:1902.10486"},{"key":"1350_CR26","doi-asserted-by":"publisher","unstructured":"Wang L, Yang K, Li C, et al (2021) Ordisco: effective and efficient usage of incremental unlabeled data for semi-supervised continual learning. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, pp 5379\u20135388. https:\/\/doi.org\/10.1109\/CVPR46437.2021.00534","DOI":"10.1109\/CVPR46437.2021.00534"},{"key":"1350_CR27","doi-asserted-by":"publisher","unstructured":"Zhai M, Chen L, Mori G (2021) Hyper-LifelongGAN: scalable lifelong learning for image conditioned generation. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition (CVPR).Nashville, TN, USA, pp 2246\u20132255. https:\/\/doi.org\/10.1109\/CVPR46437.2021.00228","DOI":"10.1109\/CVPR46437.2021.00228"},{"issue":"11","key":"1350_CR28","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M et al (2020) Generative adversarial networks. Commun ACM 63(11):139\u2013144. https:\/\/doi.org\/10.1145\/3422622","journal-title":"Commun ACM"},{"key":"1350_CR29","unstructured":"Arjovsky M, Chintala S, Bottou L (2017) Wasserstein generative adversarial networks. In: International Conference on machine learning. Sydney, Australia"},{"key":"1350_CR30","unstructured":"Kemker R, Kanan C (2017) Fearnet: brain-inspired model for incremental learning. arXiv preprint arXiv:1711.10563"},{"issue":"4","key":"1350_CR31","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1561\/2200000056","volume":"12","author":"DP Kingma","year":"2019","unstructured":"Kingma DP, Welling M (2019) An introduction to variational autoencoders. Found Trends Mach Learn 12(4):307\u2013392. https:\/\/doi.org\/10.1561\/2200000056","journal-title":"Found Trends Mach Learn"},{"key":"1350_CR32","doi-asserted-by":"publisher","unstructured":"Shi Y, Yuan L, Chen Y, et al (2021) Continual learning via bit-level information preserving. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition. ELECTR NETWORK, pp 16674\u201316683. https:\/\/doi.org\/10.1109\/cvpr46437.2021.01640","DOI":"10.1109\/cvpr46437.2021.01640"},{"key":"1350_CR33","doi-asserted-by":"publisher","unstructured":"Tang S, Chen D, Zhu J, et al (2021) Layerwise optimization by gradient decomposition for continual learning. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, pp 9634\u20139643. https:\/\/doi.org\/10.1109\/cvpr46437.2021.00951","DOI":"10.1109\/cvpr46437.2021.00951"},{"key":"1350_CR34","doi-asserted-by":"publisher","unstructured":"Cheraghian A, Rahman S, Fang P, et al (2021) Semantic-aware knowledge distillation for few-shot class-incremental learning. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, pp 2534\u20132543. https:\/\/doi.org\/10.1109\/cvpr46437.2021.00256","DOI":"10.1109\/cvpr46437.2021.00256"},{"key":"1350_CR35","doi-asserted-by":"publisher","unstructured":"Hu X, Tang K, Miao C, et al (2021) Distilling causal effect of data in class-incremental learning. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, pp 3957\u20133966. https:\/\/doi.org\/10.1109\/cvpr46437.2021.00395","DOI":"10.1109\/cvpr46437.2021.00395"},{"issue":"13","key":"1350_CR36","doi-asserted-by":"publisher","first-page":"3521","DOI":"10.1073\/pnas.1611835114","volume":"114","author":"J Kirkpatrick","year":"2017","unstructured":"Kirkpatrick J, Pascanu R, Rabinowitz N et al (2017) Overcoming catastrophic forgetting in neural networks. Proc Natl Acad Sci 114(13):3521\u20133526. https:\/\/doi.org\/10.1073\/pnas.1611835114","journal-title":"Proc Natl Acad Sci"},{"key":"1350_CR37","doi-asserted-by":"publisher","unstructured":"Zenke F, Poole B, Ganguli S (2017) Continual learning through synaptic intelligence. In: International Conference on machine learning. PMLR, pp 3987\u20133995. https:\/\/doi.org\/10.48550\/arXiv.1703.04200","DOI":"10.48550\/arXiv.1703.04200"},{"key":"1350_CR38","doi-asserted-by":"publisher","unstructured":"Aljundi R, Babiloni F, Elhoseiny M, et al (2018) Memory aware synapses: learning what (not) to forget. In: Proceedings of the European Conference on computer vision (ECCV).Springer International Publishing, pp 144\u2013161. https:\/\/doi.org\/10.1007\/978-3-030-01219-9_9","DOI":"10.1007\/978-3-030-01219-9_9"},{"key":"1350_CR39","unstructured":"Hsu Y, Liu Y, Ramasamy A, et al (2018) Re-evaluating continual learning scenarios: a categorization and case for strong baselines. arXiv preprint arXiv:1810.12488"},{"key":"1350_CR40","doi-asserted-by":"publisher","unstructured":"Van de Ven GM, Tolias AS (2019) Three scenarios for continual learning. arXiv preprint arXiv:1904.07734. https:\/\/doi.org\/10.48550\/arXiv.1904.07734","DOI":"10.48550\/arXiv.1904.07734"},{"key":"1350_CR41","doi-asserted-by":"publisher","unstructured":"Broderick T, Boyd N, Wibisono A, et al (2013). Streaming variational bayes. In: Advances in neural information processing systems. 26. https:\/\/doi.org\/10.48550\/arXiv.1307.6769","DOI":"10.48550\/arXiv.1307.6769"},{"key":"1350_CR42","doi-asserted-by":"publisher","unstructured":"Huang Z, Li J, Siniscalchi SM, et al (2014) Feature space maximum a posteriori linear regression for adaptation of deep neural networks. In: Fifteenth Annual Conference of the international speech communication association. https:\/\/doi.org\/10.21437\/Interspeech.2014-500","DOI":"10.21437\/Interspeech.2014-500"},{"key":"1350_CR43","unstructured":"Rashwan A, Zhao H, Poupart P (2016) Online and distributed bayesian moment matching for parameter learning in sum-product networks. In: Artificial intelligence and statistics. PMLR, pp 1469\u20131477"},{"key":"1350_CR44","doi-asserted-by":"publisher","unstructured":"Lange M D, Jia X, Parisot S, et al (2020) Unsupervised model personalization while preserving privacy and scalability: An open problem. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, pp 14463\u201314472. https:\/\/doi.org\/10.48550\/arXiv.2003.13296","DOI":"10.48550\/arXiv.2003.13296"},{"issue":"12","key":"1350_CR45","doi-asserted-by":"publisher","first-page":"2935","DOI":"10.1007\/978-3-319-46493-0_37","volume":"40","author":"Z Li","year":"2018","unstructured":"Li Z, Hoiem D (2018) Learning without Forgetting. IEEE Trans Pattern Anal Mach Intell 40(12):2935\u20132947. https:\/\/doi.org\/10.1007\/978-3-319-46493-0_37","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1350_CR46","doi-asserted-by":"publisher","unstructured":"Hinton G, Vinyals O, Dean J (2015) Distilling the knowledge in a neural network. 2(7) arXiv preprint arXiv:1503.02531. https:\/\/doi.org\/10.48550\/arXiv.1503.025n31","DOI":"10.48550\/arXiv.1503.025n31"},{"key":"1350_CR47","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3292359","author":"Y Kong","year":"2023","unstructured":"Kong Y, Liu L, Chen H et al (2023) Overcoming catastrophic forgetting in continual learning by exploring eigenvalues of Hessian matrix. IEEE Trans Neural Netw Learn Syst. https:\/\/doi.org\/10.1109\/TNNLS.2023.3292359","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"1350_CR48","doi-asserted-by":"publisher","first-page":"1369","DOI":"10.1016\/j.ins.2022.07.085","volume":"609","author":"M Mazur","year":"2022","unstructured":"Mazur M, Pustelnik A, Knop S et al (2022) Target layer regularization for continual learning using Cramer-Wold distance. Inf Sci 609:1369\u20131380. https:\/\/doi.org\/10.1016\/j.ins.2022.07.085","journal-title":"Inf Sci"},{"key":"1350_CR49","doi-asserted-by":"publisher","unstructured":"Rusu AA, Rabinowitz NC, Desjardins G, et al (2016) Progressive neural networks. arXiv preprint arXiv:1606.04671. https:\/\/doi.org\/10.48550\/arXiv.1606.04671","DOI":"10.48550\/arXiv.1606.04671"},{"key":"1350_CR50","doi-asserted-by":"publisher","unstructured":"Pascanu R, Bengio Y (2013) Revisiting natural gradient for deep networks. arXiv preprint arXiv:1301.3584. https:\/\/doi.org\/10.48550\/arXiv.1301.3584","DOI":"10.48550\/arXiv.1301.3584"},{"issue":"1","key":"1350_CR51","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-020-17866-2","volume":"11","author":"GM van de Ven","year":"2020","unstructured":"van de Ven GM, Siegelmann HT, Tolias AS (2020) Brain-inspired replay for continual learning with artificial neural networks. Nat Commun 11(1):1\u201314. https:\/\/doi.org\/10.1038\/s41467-020-17866-2","journal-title":"Nat Commun"},{"key":"1350_CR52","doi-asserted-by":"publisher","unstructured":"Soltau H, Saon G, Sainath TN (2014) Joint training of convolutional and non-convolutional neural networks. In: 2014 IEEE International Conference on acoustics, speech and signal processing (ICASSP). Florence, ITALY: IEEE, pp 5572\u20135576. https:\/\/doi.org\/10.1109\/ICASSP.2014.6854669","DOI":"10.1109\/ICASSP.2014.6854669"},{"key":"1350_CR53","doi-asserted-by":"publisher","unstructured":"Krizhevsky A, Hinton G (2009) Learning multiple layers of features from tiny images. https:\/\/doi.org\/10.1561\/2200000056","DOI":"10.1561\/2200000056"},{"issue":"6","key":"1350_CR54","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1109\/MSP.2012.2211477","volume":"29","author":"L Deng","year":"2012","unstructured":"Deng L (2012) The MNIST database of handwritten digit images formachine learning research [Best of the Web]. IEEE SignalProcess Mag 29(6):141\u2013142. https:\/\/doi.org\/10.1109\/MSP.2012.2211477","journal-title":"IEEE SignalProcess Mag"},{"key":"1350_CR55","doi-asserted-by":"publisher","unstructured":"Kingma D P, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980. https:\/\/doi.org\/10.48550\/arXiv.1412.6980","DOI":"10.48550\/arXiv.1412.6980"},{"key":"1350_CR56","doi-asserted-by":"publisher","unstructured":"Loshchilov I, Hutter F (2016) Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983. https:\/\/doi.org\/10.48550\/arXiv.1608.03983","DOI":"10.48550\/arXiv.1608.03983"},{"key":"1350_CR57","doi-asserted-by":"publisher","unstructured":"Chaudhry A, Dokania P K, Ajanthan T, et al (2018) Riemannian walk for incremental learning: understanding forgetting and intransigence. In: Proceedings of the European Conference on computer vision (ECCV), pp 556\u2013572. https:\/\/doi.org\/10.1007\/978-3-030-01252-6_33","DOI":"10.1007\/978-3-030-01252-6_33"}],"container-title":["Complex &amp; Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-024-01350-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-024-01350-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-024-01350-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,16]],"date-time":"2024-05-16T18:21:48Z","timestamp":1715883708000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-024-01350-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,29]]},"references-count":57,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,6]]}},"alternative-id":["1350"],"URL":"https:\/\/doi.org\/10.1007\/s40747-024-01350-1","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"value":"2199-4536","type":"print"},{"value":"2198-6053","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,29]]},"assertion":[{"value":"27 February 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 January 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 February 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}