{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T17:18:50Z","timestamp":1792257530177,"version":"4.4.0"},"reference-count":185,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2023,1,18]],"date-time":"2023-01-18T00:00:00Z","timestamp":1674000000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100010661","name":"Horizon 2020 Framework Programme","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","award":["769066"],"award-info":[{"award-number":["769066"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"publisher","award":["01IS19062"],"award-info":[{"award-number":["01IS19062"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1016\/j.neunet.2023.01.014","type":"journal-article","created":{"date-parts":[[2023,1,20]],"date-time":"2023-01-20T12:30:33Z","timestamp":1674217833000},"page":"306-336","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":98,"special_numbering":"C","title":["A wholistic view of continual learning with deep neural networks: Forgotten lessons and the bridge to active and open world learning"],"prefix":"10.1016","volume":"160","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1639-8255","authenticated-orcid":false,"given":"Martin","family":"Mundt","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongwon","family":"Hong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Iuliia","family":"Pliushch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Visvanathan","family":"Ramesh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"2","key":"10.1016\/j.neunet.2023.01.014_b1","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1016\/0885-064X(90)90006-Y","article-title":"Learning from hints in neural networks","volume":"6","author":"Abu-Mostafa","year":"1990","journal-title":"Journal of Complexity"},{"key":"10.1016\/j.neunet.2023.01.014_b2","unstructured":"Achille,\u00a0A., Eccles,\u00a0T., Matthey,\u00a0L., Burgess,\u00a0C. P., Watters,\u00a0N., Lerchner,\u00a0A., et al. (2018). Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies. In Neural information processing systems."},{"key":"10.1016\/j.neunet.2023.01.014_b3","unstructured":"Ahn,\u00a0H., Cha,\u00a0S., Lee,\u00a0D., & Moon,\u00a0T. (2019). Uncertainty-based Continual Learning with Adaptive Regularization. In Neural information processing systems."},{"issue":"4","key":"10.1016\/j.neunet.2023.01.014_b4","doi-asserted-by":"crossref","first-page":"991","DOI":"10.1152\/physrev.00004.2014","article-title":"Regulation and function of adult neurogenesis: from genes to cognition","volume":"94","author":"Aimone","year":"2014","journal-title":"Physiological Reviews"},{"key":"10.1016\/j.neunet.2023.01.014_b5","doi-asserted-by":"crossref","unstructured":"Aljundi,\u00a0R., Babiloni,\u00a0F., Elhoseiny,\u00a0M., Rohrbach,\u00a0M., & Tuytelaars,\u00a0T. (2018). Memory Aware Synapses: Learning what (not) to forget. In European conference on computer vision.","DOI":"10.1007\/978-3-030-01219-9_9"},{"key":"10.1016\/j.neunet.2023.01.014_b6","doi-asserted-by":"crossref","unstructured":"Aljundi,\u00a0R., Chakravarty,\u00a0P., & Tuytelaars,\u00a0T. (2017). Expert gate: Lifelong learning with a network of experts. In Computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2017.753"},{"key":"10.1016\/j.neunet.2023.01.014_b7","first-page":"989","article-title":"Avoiding catastrophic forgetting by coupling two reverberating neural networks","author":"Ans","year":"1997","journal-title":"Life Sciences"},{"issue":"4","key":"10.1016\/j.neunet.2023.01.014_b8","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1080\/09540098908915647","article-title":"Dynamic node creation in backpropagation networks","volume":"1","author":"Ash","year":"1989","journal-title":"Connection Science"},{"key":"10.1016\/j.neunet.2023.01.014_b9","unstructured":"Atlas,\u00a0L. E., Cohn,\u00a0D. A., Ladner,\u00a0R., El-Sharkawi,\u00a0M. A., Marks,\u00a0R. J., Aggoune,\u00a0M. E., et al. (1990). Training connectionist networks with queries and selective sampling. In Neural information processing systems."},{"key":"10.1016\/j.neunet.2023.01.014_b10","unstructured":"Bachem,\u00a0O., Lucic,\u00a0M., & Krause,\u00a0A. (2015). Coresets for Nonparametric Estimation - the Case of DP-Means. In International conference on machine learning, vol. 37 (pp. 209\u2013217)."},{"key":"10.1016\/j.neunet.2023.01.014_b11","first-page":"1823","article-title":"Classification with a reject option using a hinge loss","volume":"9","author":"Bartlett","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"10.1016\/j.neunet.2023.01.014_b12","series-title":"Interpreting and explaining deep neural networks for classification of audio signals","author":"Becker","year":"2018"},{"key":"10.1016\/j.neunet.2023.01.014_b13","doi-asserted-by":"crossref","unstructured":"Bell,\u00a0S., Upchurch,\u00a0P., Snavely,\u00a0N., & Bala,\u00a0K. (2015). Material recognition in the wild with the Materials in Context Database. In Computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2015.7298970"},{"key":"10.1016\/j.neunet.2023.01.014_b14","doi-asserted-by":"crossref","unstructured":"Beluch,\u00a0W. H., Genewein,\u00a0T., N\u00fcrnberger,\u00a0A., & K\u00f6hler,\u00a0J. M. (2018). The Power of Ensembles for Active Learning in Image Classification. In Computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2018.00976"},{"key":"10.1016\/j.neunet.2023.01.014_b15","doi-asserted-by":"crossref","unstructured":"Bendale,\u00a0A., & Boult,\u00a0T. E. (2015). Towards Open World Recognition. In Computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2015.7298799"},{"key":"10.1016\/j.neunet.2023.01.014_b16","doi-asserted-by":"crossref","unstructured":"Bendale,\u00a0A., & Boult,\u00a0T. E. (2016). Towards Open Set Deep Networks. In Computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2016.173"},{"key":"10.1016\/j.neunet.2023.01.014_b17","doi-asserted-by":"crossref","unstructured":"Bengio,\u00a0Y., Louradour,\u00a0J., Collobert,\u00a0R., & Weston,\u00a0J. (2009). Curriculum learning. In International conference on machine learning.","DOI":"10.1145\/1553374.1553380"},{"issue":"4","key":"10.1016\/j.neunet.2023.01.014_b18","first-page":"217","article-title":"Novelty detection and neural network validation","volume":"141","author":"Bishop","year":"1994","journal-title":"IEE Proceedings: Vision, Image and Signal Processing"},{"key":"10.1016\/j.neunet.2023.01.014_b19","series-title":"Online learning in neural networks","first-page":"9","article-title":"Online learning and stochastic approximations","author":"Bottou","year":"1999"},{"key":"10.1016\/j.neunet.2023.01.014_b20","doi-asserted-by":"crossref","unstructured":"Boult,\u00a0T. E., Cruz,\u00a0S., Dhamija,\u00a0A. R., Gunther,\u00a0M., Henrydoss,\u00a0J., & Scheirer,\u00a0W. J. (2019). Learning and the Unknown : Surveying Steps Toward Open World Recognition. In AAAI conference on artificial intelligence.","DOI":"10.1609\/aaai.v33i01.33019801"},{"key":"10.1016\/j.neunet.2023.01.014_b21","unstructured":"Burgess,\u00a0C. P., Higgins,\u00a0I., Pal,\u00a0A., Matthey,\u00a0L., Watters,\u00a0N., Desjardins,\u00a0G., et al. (2017). Understanding disentangling in beta-VAE. In Neural information processing systems (NeurIPS), Workshop on learning disentangled representations."},{"key":"10.1016\/j.neunet.2023.01.014_b22","doi-asserted-by":"crossref","unstructured":"Carlson,\u00a0A., Betteridge,\u00a0J., Kisiel,\u00a0B., Settles,\u00a0B., Hruschka,\u00a0E. R., & Mitchell,\u00a0T. M. (2010). Toward an Architecture for Never-Ending Language Learning. In AAAI conference on artificial intelligence.","DOI":"10.1609\/aaai.v24i1.7519"},{"key":"10.1016\/j.neunet.2023.01.014_b23","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1023\/A:1007379606734","article-title":"Multitask learning","volume":"28","author":"Caruana","year":"1997","journal-title":"Machine Learning"},{"key":"10.1016\/j.neunet.2023.01.014_b24","doi-asserted-by":"crossref","unstructured":"Chaudhry,\u00a0A., Dokania,\u00a0P. K., Ajanthan,\u00a0T., & Torr,\u00a0P. H. S. (2018). Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence. In European conference on computer vision.","DOI":"10.1007\/978-3-030-01252-6_33"},{"key":"10.1016\/j.neunet.2023.01.014_b25","unstructured":"Chaudhry,\u00a0A., Ranzato,\u00a0M., Rohrbach,\u00a0M., & Elhoseiny,\u00a0M. (2019). Efficient lifelong learning with A-GEM. In International conference on learning representations."},{"key":"10.1016\/j.neunet.2023.01.014_b26","unstructured":"Chen,\u00a0T., Goodfellow,\u00a0I., & Shlens,\u00a0J. (2016). Net2Net: Accelerating learning via knowledge transfer. In International conference on learning representations."},{"key":"10.1016\/j.neunet.2023.01.014_b27","series-title":"Lifelong machine learning","volume":"vol. 33","author":"Chen","year":"2017"},{"key":"10.1016\/j.neunet.2023.01.014_b28","doi-asserted-by":"crossref","unstructured":"Chen,\u00a0X., Shrivastava,\u00a0A., & Gupta,\u00a0A. (2013). NEIL: Extracting Visual Knowledge from Web Data. In International conference on computer vision.","DOI":"10.1109\/ICCV.2013.178"},{"key":"10.1016\/j.neunet.2023.01.014_b29","doi-asserted-by":"crossref","unstructured":"Cimpoi,\u00a0M., Maji,\u00a0S., & Vedaldi,\u00a0A. (2015). Deep convolutional filter banks for texture recognition and segmentation. In Computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2015.7299007"},{"key":"10.1016\/j.neunet.2023.01.014_b30","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1613\/jair.295","article-title":"Active learning with statistical models","volume":"4","author":"Cohn","year":"1996","journal-title":"Journal of Artificial Intelligence Research"},{"key":"10.1016\/j.neunet.2023.01.014_b31","unstructured":"Dasgupta,\u00a0S. (2005). Analysis of a greedy active learning strategy. In Neural information processing systems."},{"key":"10.1016\/j.neunet.2023.01.014_b32","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2021.3057446","article-title":"A continual learning survey: Defying forgetting in classification tasks","author":"De Lange","year":"2021","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"10.1016\/j.neunet.2023.01.014_b33","unstructured":"Dhamija,\u00a0A. R., G\u00fcnther,\u00a0M., & Boult,\u00a0T. E. (2018). Reducing Network Agnostophobia. In Neural information processing systems."},{"key":"10.1016\/j.neunet.2023.01.014_b34","unstructured":"D\u00edaz-Rodr\u00edguez,\u00a0N., Lomonaco,\u00a0V., Filliat,\u00a0D., & Maltoni,\u00a0D. (2018). Don\u2019t forget, there is more than forgetting: new metrics for Continual Learning. In Neural information processing systems (NeurIPS), Continual learning workshop."},{"key":"10.1016\/j.neunet.2023.01.014_b35","doi-asserted-by":"crossref","unstructured":"Draelos,\u00a0T. J., Miner,\u00a0N. E., Lamb,\u00a0C. C., Cox,\u00a0J. A., Vineyard,\u00a0C. M., Carlson,\u00a0K. D., et al. (2017). Neurogenesis deep learning: Extending deep networks to accommodate new classes. In International joint conference on neural networks (pp. 526\u2013533).","DOI":"10.1109\/IJCNN.2017.7965898"},{"key":"10.1016\/j.neunet.2023.01.014_b36","unstructured":"Ebrahimi,\u00a0S., Elhoseiny,\u00a0M., Darrell,\u00a0T., & Rohrbach,\u00a0M. (2020). Uncertainty-guided Continual Learning with Bayesian Neural Networks. In International conference on learning representations."},{"key":"10.1016\/j.neunet.2023.01.014_b37","unstructured":"Farquhar,\u00a0S., & Gal,\u00a0Y. (2018a). A Unifying Bayesian View of Continual Learning. In Neural information processing systems (NeurIPS) Bayesian deep learning workshop."},{"key":"10.1016\/j.neunet.2023.01.014_b38","unstructured":"Farquhar,\u00a0S., & Gal,\u00a0Y. (2018b). Towards Robust Evaluations of Continual Learning. In International conference on machine learning (ICML), lifelong learning: A reinforcement learning approach workshop."},{"key":"10.1016\/j.neunet.2023.01.014_b39","doi-asserted-by":"crossref","unstructured":"Fei,\u00a0G., Wang,\u00a0S., & Liu,\u00a0B. (2016). Learning cumulatively to become more knowledgeable. In Proceedings of the ACM SIGKDD international conference on knowledge discovery and data mining (pp. 1565\u20131574).","DOI":"10.1145\/2939672.2939835"},{"issue":"4","key":"10.1016\/j.neunet.2023.01.014_b40","doi-asserted-by":"crossref","first-page":"594","DOI":"10.1109\/TPAMI.2006.79","article-title":"One-shot learning of object categories","volume":"28","author":"Fei-Fei","year":"2006","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"10.1016\/j.neunet.2023.01.014_b41","doi-asserted-by":"crossref","unstructured":"Feng,\u00a0Q., Kang,\u00a0G., Fan,\u00a0H., & Yang,\u00a0Y. (2019). Attract or Distract: Exploit the Margin of Open Set. In International conference on computer vision.","DOI":"10.1109\/ICCV.2019.00808"},{"key":"10.1016\/j.neunet.2023.01.014_b42","series-title":"PathNet: Evolution channels gradient descent in super neural networks","author":"Fernando","year":"2017"},{"key":"10.1016\/j.neunet.2023.01.014_b43","unstructured":"Fink,\u00a0M. (2005). Object classification from a single example utilizing class relevance metrics. In Neural information processing systems."},{"issue":"3\u20134","key":"10.1016\/j.neunet.2023.01.014_b44","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1080\/09540099208946624","article-title":"Semi-distributed representations and catastrophic forgetting in connectionist networks","volume":"4","author":"French","year":"1992","journal-title":"Connection Science"},{"issue":"4","key":"10.1016\/j.neunet.2023.01.014_b45","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1080\/095400997116595","article-title":"Pseudo-recurrent connectionist networks: An approach to the \u2018sensitivity-stability\u2019 dilemma","volume":"9","author":"French","year":"1997","journal-title":"Connection Science"},{"issue":"1","key":"10.1016\/j.neunet.2023.01.014_b46","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1006\/jcss.1997.1504","article-title":"A decision theoretic generalisation of online learning and an application to boosting","volume":"55","author":"Freund","year":"1997","journal-title":"Computer and System Sciences"},{"key":"10.1016\/j.neunet.2023.01.014_b47","unstructured":"Gal,\u00a0Y., & Ghahramani,\u00a0Z. (2015). Dropout as a Bayesian Approximation : Representing Model Uncertainty in Deep Learning. In International conference on machine learning, vol. 48."},{"key":"10.1016\/j.neunet.2023.01.014_b48","unstructured":"Gal,\u00a0Y., Islam,\u00a0R., & Ghahramani,\u00a0Z. (2017). Deep Bayesian Active Learning with Image Data. In International conference on machine learning."},{"key":"10.1016\/j.neunet.2023.01.014_b49","unstructured":"Geifman,\u00a0Y., & El-Yaniv,\u00a0R. (2019). Deep Active Learning with a Neural Architecture Search. In Neural information processing systems."},{"key":"10.1016\/j.neunet.2023.01.014_b50","unstructured":"Geirhos,\u00a0R., Michaelis,\u00a0C., Wichmann,\u00a0F. A., Rubisch,\u00a0P., Bethge,\u00a0M., & Brendel,\u00a0W. (2019). Imagenet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. In International conference on learning representations."},{"issue":"5","key":"10.1016\/j.neunet.2023.01.014_b51","doi-asserted-by":"crossref","first-page":"924","DOI":"10.1007\/s12559-016-9389-5","article-title":"A bio-inspired incremental learning architecture for applied perceptual problems","volume":"8","author":"Gepperth","year":"2016","journal-title":"Cognitive Computation"},{"issue":"C","key":"10.1016\/j.neunet.2023.01.014_b52","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1016\/0304-3975(85)90224-5","article-title":"Clustering to minimize the maximum intercluster distance","volume":"38","author":"Gonzalez","year":"1985","journal-title":"Theoretical Computer Science"},{"key":"10.1016\/j.neunet.2023.01.014_b53","unstructured":"Goodfellow,\u00a0I. J., Pouget-Abadie,\u00a0J., Mirza,\u00a0M., Xu,\u00a0B., Warde-Farley,\u00a0D., Ozair,\u00a0S., et al. (2014). Generative Adversarial Nets. In Neural information processing systems."},{"issue":"1","key":"10.1016\/j.neunet.2023.01.014_b54","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1038\/35036235","article-title":"Neurogenesis in the adult brain: Death of a dogma","volume":"1","author":"Gross","year":"2000","journal-title":"Nature Reviews Neuroscience"},{"key":"10.1016\/j.neunet.2023.01.014_b55","unstructured":"Hacohen,\u00a0G., Choshen,\u00a0L., & Weinshall,\u00a0D. (2020). Let\u2019s Agree to Agree: Neural Networks Share Classification Order on Real Datasets. In International conference on learning representations."},{"key":"10.1016\/j.neunet.2023.01.014_b56","doi-asserted-by":"crossref","unstructured":"He,\u00a0K., Zhang,\u00a0X., Ren,\u00a0S., & Sun,\u00a0J. (2015). Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In International conference on computer vision.","DOI":"10.1109\/ICCV.2015.123"},{"key":"10.1016\/j.neunet.2023.01.014_b57","doi-asserted-by":"crossref","unstructured":"He,\u00a0K., Zhang,\u00a0X., Ren,\u00a0S., & Sun,\u00a0J. (2016). Deep Residual Learning for Image Recognition. In Computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.neunet.2023.01.014_b58","series-title":"The organization of behavior; a neuropsychological theory","author":"Hebb","year":"1949"},{"key":"10.1016\/j.neunet.2023.01.014_b59","unstructured":"Hendrycks,\u00a0D., & Dietterich,\u00a0T. (2019). Benchmarking neural network robustness to common corruptions and perturbations. In International conference on learning representations."},{"key":"10.1016\/j.neunet.2023.01.014_b60","unstructured":"Hendrycks,\u00a0D., & Gimpel,\u00a0K. (2017). A baseline for detecting misclassified and out-of-distribution examples in neural networks. In International conference on learning representations."},{"issue":"C","key":"10.1016\/j.neunet.2023.01.014_b61","first-page":"199","article-title":"On-line learning processes in artificial neural networks","volume":"51","author":"Heskes","year":"1993","journal-title":"Mathematical Foundations of Neural Networks"},{"key":"10.1016\/j.neunet.2023.01.014_b62","unstructured":"Hess,\u00a0T., Mundt,\u00a0M., Pliushch,\u00a0I., & Ramesh,\u00a0V. (2021). A Procedural World Generation Framework for Systematic Evaluation of Continual Learning. In Neural information processing systems (NeurIPS), dataset and benchmarks track."},{"key":"10.1016\/j.neunet.2023.01.014_b63","unstructured":"Hinton,\u00a0G. E., Vinyals,\u00a0O., & Dean,\u00a0J. (2014). Distilling the Knowledge in a Neural Network. In NeurIPS deep learning workshop."},{"issue":"8","key":"10.1016\/j.neunet.2023.01.014_b64","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Computation"},{"key":"10.1016\/j.neunet.2023.01.014_b65","unstructured":"Hoffman,\u00a0M. D., & Johnson,\u00a0M. J. (2016). ELBO surgery: yet another way to carve up the variational evidence lower bound. In Neural information processing systems (NeurIPS), advances in approximate bayesian inference workshop."},{"key":"10.1016\/j.neunet.2023.01.014_b66","unstructured":"Ilyas,\u00a0A., Santurkar,\u00a0S., Tsipras,\u00a0D., Engstrom,\u00a0L., Tran,\u00a0B., & Madry,\u00a0A. (2019). Adversarial Examples are not Bugs, they are Features. In Neural information processing systems."},{"key":"10.1016\/j.neunet.2023.01.014_b67","unstructured":"Ioffe,\u00a0S., & Szegedy,\u00a0C. (2015). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. In International conference on machine learning."},{"key":"10.1016\/j.neunet.2023.01.014_b68","doi-asserted-by":"crossref","unstructured":"Isele,\u00a0D., & Cosgun,\u00a0A. (2018). Selective experience replay for lifelong learning. In AAAI conference on artificial intelligence.","DOI":"10.1609\/aaai.v32i1.11595"},{"key":"10.1016\/j.neunet.2023.01.014_b69","doi-asserted-by":"crossref","unstructured":"Javed,\u00a0K., & Shafait,\u00a0F. (2018). Revisiting Distillation and Incremental Classifier Learning. In Asian conference on computer vision.","DOI":"10.1007\/978-3-030-20876-9_1"},{"key":"10.1016\/j.neunet.2023.01.014_b70","doi-asserted-by":"crossref","unstructured":"Joshi,\u00a0A. J., Porikli,\u00a0F., & Papanikolopoulos,\u00a0N. (2009). Multi-class active learning for image classification. In Computer vision and pattern recognition.","DOI":"10.1109\/CVPRW.2009.5206627"},{"key":"10.1016\/j.neunet.2023.01.014_b71","doi-asserted-by":"crossref","unstructured":"K\u00e4ding,\u00a0C., Freytag,\u00a0A., Rodner,\u00a0E., Perino,\u00a0A., & Denzler,\u00a0J. (2016). Large-scale active learning with approximations of expected model output changes. In German conference on pattern recognition.","DOI":"10.1007\/978-3-319-45886-1_15"},{"key":"10.1016\/j.neunet.2023.01.014_b72","series-title":"Active and continuous exploration with deep neural networks and expected model output changes","author":"K\u00e4ding","year":"2016"},{"key":"10.1016\/j.neunet.2023.01.014_b73","unstructured":"Kemker,\u00a0R., & Kanan,\u00a0C. (2018). FearNet: Brain-inspired model for incremental learning. In International conference on learning representations."},{"key":"10.1016\/j.neunet.2023.01.014_b74","doi-asserted-by":"crossref","unstructured":"Kemker,\u00a0R., McClure,\u00a0M., Abitino,\u00a0A., Hayes,\u00a0T., & Kanan,\u00a0C. (2018). Measuring Catastrophic Forgetting in Neural Networks. In AAAI conference on artificial intelligence.","DOI":"10.1609\/aaai.v32i1.11651"},{"key":"10.1016\/j.neunet.2023.01.014_b75","doi-asserted-by":"crossref","unstructured":"Kendall,\u00a0A., Badrinarayanan,\u00a0V., & Cipolla,\u00a0R. (2017). Bayesian segnet: Model uncertainty in deep convolutional encoder-decoder architectures for scene understanding. In British machine vision conference.","DOI":"10.5244\/C.31.57"},{"key":"10.1016\/j.neunet.2023.01.014_b76","unstructured":"Kingma,\u00a0D. P., & Ba,\u00a0J. L. (2015). Adam: a Method for Stochastic Optimization. In International conference on learning representations."},{"key":"10.1016\/j.neunet.2023.01.014_b77","unstructured":"Kingma,\u00a0D. P., & Welling,\u00a0M. (2013). Auto-Encoding Variational Bayes. In International conference on learning representations."},{"issue":"13","key":"10.1016\/j.neunet.2023.01.014_b78","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"Kirkpatrick","year":"2017","journal-title":"Proceedings of the National Academy of Sciences (PNAS)"},{"key":"10.1016\/j.neunet.2023.01.014_b79","unstructured":"Konyushkova,\u00a0K., Raphael,\u00a0S., & Fua,\u00a0P. (2017). Learning active learning from data. In Neural information processing systems."},{"key":"10.1016\/j.neunet.2023.01.014_b80","unstructured":"Krizhevsky,\u00a0A. (2009). Learning multiple layers of features from tiny images: Technical Report, Toronto."},{"issue":"7","key":"10.1016\/j.neunet.2023.01.014_b81","doi-asserted-by":"crossref","first-page":"512","DOI":"10.1016\/j.tics.2016.05.004","article-title":"What learning systems do intelligent agents need? complementary learning systems theory updated","volume":"20","author":"Kumaran","year":"2016","journal-title":"Trends in Cognitive Sciences"},{"key":"10.1016\/j.neunet.2023.01.014_b82","doi-asserted-by":"crossref","unstructured":"Lampert,\u00a0C. H., Nickisch,\u00a0H., & Harmeling,\u00a0S. (2009). Learning to detect unseen object classes by between-class attribute transfer. In Computer vision and pattern recognition.","DOI":"10.1109\/CVPRW.2009.5206594"},{"issue":"1","key":"10.1016\/j.neunet.2023.01.014_b83","doi-asserted-by":"crossref","DOI":"10.1038\/s41467-019-08987-4","article-title":"Unmasking clever hans predictors and assessing what machines really learn","volume":"10","author":"Lapuschkin","year":"2019","journal-title":"Nature Communications"},{"issue":"11","key":"10.1016\/j.neunet.2023.01.014_b84","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proceedings of the IEEE"},{"key":"10.1016\/j.neunet.2023.01.014_b85","unstructured":"Lee,\u00a0S. W., Kim,\u00a0J. H., Jun,\u00a0J., Ha,\u00a0J. W., & Zhang,\u00a0B. T. (2017). Overcoming catastrophic forgetting by incremental moment matching. In Neural information processing systems (pp. 4653\u20134663)."},{"key":"10.1016\/j.neunet.2023.01.014_b86","unstructured":"Lee,\u00a0K., Lee,\u00a0H., Lee,\u00a0K., & Shin,\u00a0J. (2018a). Training Confidence-Calibrated Classifiers for Detecting Out-of-Distribution Samples. In International conference on learning representations."},{"key":"10.1016\/j.neunet.2023.01.014_b87","unstructured":"Lee,\u00a0K., Lee,\u00a0K., Lee,\u00a0H., & Shin,\u00a0J. (2018b). A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks. In Neural information processing systems."},{"key":"10.1016\/j.neunet.2023.01.014_b88","doi-asserted-by":"crossref","unstructured":"Lesort,\u00a0T., Caselles-Dupr\u00e9,\u00a0H., Garcia-Ortiz,\u00a0M., Stoian,\u00a0A., & Filliat,\u00a0D. (2019). Generative Models from the perspective of Continual Learning. In International joint conference on neural networks.","DOI":"10.1109\/IJCNN.2019.8851986"},{"key":"10.1016\/j.neunet.2023.01.014_b89","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1016\/j.inffus.2019.12.004","article-title":"Continual learning for robotics: Definition, framework, learning strategies, opportunities and challenges","volume":"58","author":"Lesort","year":"2020","journal-title":"Information Fusion"},{"key":"10.1016\/j.neunet.2023.01.014_b90","doi-asserted-by":"crossref","unstructured":"Lewis,\u00a0D. D., & Gale,\u00a0W. A. (1994). A sequential algorithm for training text classifiers. In International ACM SIGIR conference on research and development in information retrieval.","DOI":"10.1007\/978-1-4471-2099-5_1"},{"key":"10.1016\/j.neunet.2023.01.014_b91","unstructured":"Li,\u00a0Y., Bradshaw,\u00a0J., & Sharma,\u00a0Y. (2019). Are Generative Classifiers More Robust to Adversarial Attacks?. In International conference on machine learning."},{"key":"10.1016\/j.neunet.2023.01.014_b92","doi-asserted-by":"crossref","unstructured":"Li,\u00a0X., & Guo,\u00a0Y. (2013). Adaptive active learning for image classification. In Computer vision and pattern recognition (pp. 859\u2013866).","DOI":"10.1109\/CVPR.2013.116"},{"key":"10.1016\/j.neunet.2023.01.014_b93","doi-asserted-by":"crossref","unstructured":"Li,\u00a0Z., & Hoiem,\u00a0D. (2016). Learning without forgetting. In European conference on computer vision.","DOI":"10.1007\/978-3-319-46493-0_37"},{"issue":"11","key":"10.1016\/j.neunet.2023.01.014_b94","doi-asserted-by":"crossref","first-page":"1686","DOI":"10.1109\/TPAMI.2005.224","article-title":"Open set face recognition using transduction","volume":"27","author":"Li","year":"2005","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2023.01.014_b95","unstructured":"Li,\u00a0X., Zhou,\u00a0Y., Wu,\u00a0T., Socher,\u00a0R., & Xiong,\u00a0C. (2019). Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting. In International conference on machine learning."},{"key":"10.1016\/j.neunet.2023.01.014_b96","unstructured":"Liang,\u00a0S., Li,\u00a0Y., & Srikant,\u00a0R. (2018). Enhancing the Reliability of Out-of-distribution Image Detection in Neural Networks. In International conference on learning representations."},{"key":"10.1016\/j.neunet.2023.01.014_b97","unstructured":"Lin,\u00a0Z., Pathak,\u00a0D., & Ramanan,\u00a0D. (2021). The CLEAR Benchmark: Continual LEArning on Real-World Imagery. In Neural information processing systems (NeurIPS), dataset and benchmarks track."},{"key":"10.1016\/j.neunet.2023.01.014_b98","doi-asserted-by":"crossref","unstructured":"Lis,\u00a0K., Nakka,\u00a0K., Fua,\u00a0P., & Salzmann,\u00a0M. (2019). Detecting the Unexpected via Image Resynthesis. In International conference on computer vision.","DOI":"10.1109\/ICCV.2019.00224"},{"key":"10.1016\/j.neunet.2023.01.014_b99","unstructured":"Lopez-Paz,\u00a0D., & Ranzato,\u00a0M. (2017). Gradient Episodic Memory for Continual Learning. In Neural information processing systems."},{"issue":"4","key":"10.1016\/j.neunet.2023.01.014_b100","doi-asserted-by":"crossref","first-page":"590","DOI":"10.1162\/neco.1992.4.4.590","article-title":"Information-based objective functions for active data selection","volume":"4","author":"MacKay","year":"1992","journal-title":"Neural Computation"},{"key":"10.1016\/j.neunet.2023.01.014_b101","doi-asserted-by":"crossref","unstructured":"Mahapatra,\u00a0D., Bozorgtabar,\u00a0B., Thiran,\u00a0J. P., & Reyes,\u00a0M. (2018). Efficient active learning for image classification and segmentation using a sample selection and conditional generative adversarial network. In Medical image computing and computer assisted intervention.","DOI":"10.1007\/978-3-030-00934-2_65"},{"key":"10.1016\/j.neunet.2023.01.014_b102","doi-asserted-by":"crossref","unstructured":"Mallya,\u00a0A., Davis,\u00a0D., & Lazebnik,\u00a0S. (2018). Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights. In European conference on computer vision.","DOI":"10.1007\/978-3-030-01225-0_5"},{"key":"10.1016\/j.neunet.2023.01.014_b103","unstructured":"Matan,\u00a0O., Kiang,\u00a0R., Stenard,\u00a0C. E., Boser,\u00a0B. E., Denker,\u00a0J., Henderson,\u00a0D., et al. (1990). Handwritten Character Recognition Using Neural Network Architectures. In 4th USPS advanced technology conference, vol. 2, no. 5 (pp. 1003\u20131011)."},{"key":"10.1016\/j.neunet.2023.01.014_b104","unstructured":"Mathieu,\u00a0E., Rainforth,\u00a0T., Siddharth,\u00a0N., & Teh,\u00a0Y. W. (2019). Disentangling disentanglement in variational autoencoders. In International conference on machine learning (pp. 7744\u20137754)."},{"key":"10.1016\/j.neunet.2023.01.014_b105","doi-asserted-by":"crossref","unstructured":"Mayer,\u00a0C., & Timofte,\u00a0R. (2020). Adversarial sampling for active learning. In Winter conference on applications of computer vision.","DOI":"10.1109\/WACV45572.2020.9093556"},{"key":"10.1016\/j.neunet.2023.01.014_b106","unstructured":"McCallum,\u00a0A. K., & Nigam,\u00a0K. (1998). Employing EM and Pool-Based Active Learning for Text Classification. In International conference on machine learning."},{"issue":"3","key":"10.1016\/j.neunet.2023.01.014_b107","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1037\/0033-295X.102.3.419","article-title":"Why there are complementary learning systems in the hippocampus and neocortex: insights from the successes and failures of connectionist models of learning and memory","volume":"102","author":"McClelland","year":"1995","journal-title":"Psychological Review"},{"issue":"C","key":"10.1016\/j.neunet.2023.01.014_b108","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/S0079-7421(08)60536-8","article-title":"Catastrophic interference in connectionist networks : The sequential learning problem","volume":"24","author":"McCloskey","year":"1989","journal-title":"Psychology of Learning and Motivation - Advances in Research and Theory"},{"key":"10.1016\/j.neunet.2023.01.014_b109","doi-asserted-by":"crossref","unstructured":"Miller,\u00a0D., Nicholson,\u00a0L., Dayoub,\u00a0F., & Sunderhauf,\u00a0N. (2018). Dropout Sampling for Robust Object Detection in Open-Set Conditions. In IEEE international conference on robotics and automation (pp. 3243\u20133249).","DOI":"10.1109\/ICRA.2018.8460700"},{"issue":"2","key":"10.1016\/j.neunet.2023.01.014_b110","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1016\/0004-3702(82)90040-6","article-title":"Generalization as search","volume":"18","author":"Mitchell","year":"1982","journal-title":"Artificial Intelligence"},{"key":"10.1016\/j.neunet.2023.01.014_b111","doi-asserted-by":"crossref","unstructured":"Mitchell,\u00a0T. M., Cohen,\u00a0W., Hruschka,\u00a0E. R., Talukdar,\u00a0P., Betteridge,\u00a0J., Carlson,\u00a0A., et al. (2015). Never-Ending Learning. In AAAI conference on artificial intelligence.","DOI":"10.1609\/aaai.v29i1.9498"},{"issue":"4","key":"10.1016\/j.neunet.2023.01.014_b112","doi-asserted-by":"crossref","DOI":"10.3390\/jimaging8040093","article-title":"Unified probabilistic deep continual learning through generative replay and open set recognition","volume":"8","author":"Mundt","year":"2022","journal-title":"Journal of Imaging"},{"key":"10.1016\/j.neunet.2023.01.014_b113","doi-asserted-by":"crossref","unstructured":"Mundt,\u00a0M., Pliushch,\u00a0I., Majumder,\u00a0S., & Ramesh,\u00a0V. (2019). Open Set Recognition Through Deep Neural Network Uncertainty: Does Out-of-Distribution Detection Require Generative Classifiers?. In International conference on computer vision (ICCV), First workshop on statistical deep learning for computer vision.","DOI":"10.1109\/ICCVW.2019.00098"},{"key":"10.1016\/j.neunet.2023.01.014_b114","series-title":"Human-in-the-loop machine learning","first-page":"325","author":"Munro","year":"2020"},{"key":"10.1016\/j.neunet.2023.01.014_b115","unstructured":"Nalisnick,\u00a0E., Matsukawa,\u00a0A., Teh,\u00a0Y. W., Gorur,\u00a0D., & Lakshminarayanan,\u00a0B. (2019). Do Deep Generative Models Know What They Don\u2019t Know?. In International conference on learning representations."},{"issue":"2","key":"10.1016\/j.neunet.2023.01.014_b116","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1016\/j.surge.2010.01.006","article-title":"Known knowns, known unknowns and unknown unknowns: A 2010 update on carotid artery disease","volume":"8","author":"Naylor","year":"2010","journal-title":"Surgeon"},{"key":"10.1016\/j.neunet.2023.01.014_b117","unstructured":"Nguyen,\u00a0C. V., Li,\u00a0Y., Bui,\u00a0T. D., & Turner,\u00a0R. E. (2018). Variational Continual Learning. In International conference on learning representations."},{"key":"10.1016\/j.neunet.2023.01.014_b118","doi-asserted-by":"crossref","unstructured":"Nguyen,\u00a0H. T., & Smeulders,\u00a0A. (2004). Active learning using pre-clustering. In International conference on machine learning.","DOI":"10.1145\/1015330.1015349"},{"key":"10.1016\/j.neunet.2023.01.014_b119","doi-asserted-by":"crossref","unstructured":"Oquab,\u00a0M., Bottou,\u00a0L., Laptev,\u00a0I., & Sivic,\u00a0J. (2014). Learning and transferring mid-level image representations using convolutional neural networks. In Computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2014.222"},{"key":"10.1016\/j.neunet.2023.01.014_b120","unstructured":"Ovadia,\u00a0Y., Fertig,\u00a0E., Ren,\u00a0J., Nado,\u00a0Z., Sculley,\u00a0D., Nowozin,\u00a0S., et al. (2019). Can You Trust Your Model\u2019s Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift. In Neural information processing systems."},{"issue":"10","key":"10.1016\/j.neunet.2023.01.014_b121","doi-asserted-by":"crossref","DOI":"10.1109\/TKDE.2009.191","article-title":"A survey on transfer learning","volume":"22","author":"Pan","year":"2010","journal-title":"IEEE Transactions on Knowledge and Data Engineering (TKDE)"},{"key":"10.1016\/j.neunet.2023.01.014_b122","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1016\/j.neunet.2019.01.012","article-title":"Continual lifelong learning with neural networks: A review","volume":"113","author":"Parisi","year":"2019","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2023.01.014_b123","doi-asserted-by":"crossref","unstructured":"Park,\u00a0D., Hong,\u00a0S., Han,\u00a0B., & Lee,\u00a0K. M. (2019). Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation. In International conference on computer vision.","DOI":"10.1109\/ICCV.2019.00343"},{"key":"10.1016\/j.neunet.2023.01.014_b124","doi-asserted-by":"crossref","unstructured":"Perera,\u00a0P., Nallapati,\u00a0R., & Xiang,\u00a0B. (2019). OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representations. In Computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2019.00301"},{"key":"10.1016\/j.neunet.2023.01.014_b125","unstructured":"Pf\u00fclb,\u00a0B., & Gepperth,\u00a0A. (2019). A Comprehensive, Application-Oriented Study of Catastrophic Forgetting in DNNs. In International conference on learning representations."},{"key":"10.1016\/j.neunet.2023.01.014_b126","doi-asserted-by":"crossref","unstructured":"Pliushch,\u00a0I., Mundt,\u00a0M., Lupp,\u00a0N., & Ramesh,\u00a0V. (2022). When Deep Classifiers Agree: Analyzing Correlations between Learning Order and Image Statistics. In European conference on computer vision.","DOI":"10.1007\/978-3-031-20074-8_23"},{"key":"10.1016\/j.neunet.2023.01.014_b127","unstructured":"Pratt,\u00a0L. Y. (1993). Discriminability-Based Transfer between Neural Networks. In Neural information processing systems."},{"key":"10.1016\/j.neunet.2023.01.014_b128","unstructured":"Pratt,\u00a0L. Y., Mostow,\u00a0J., & Kamm,\u00a0C. A. (1991). Direct Transfer of Learned Information Among Neural Networks. In AAAI conference on artificial intelligence."},{"key":"10.1016\/j.neunet.2023.01.014_b129","doi-asserted-by":"crossref","unstructured":"Rannen,\u00a0A., Aljundi,\u00a0R., Blaschko,\u00a0M. B., & Tuytelaars,\u00a0T. (2017). Encoder Based Lifelong Learning. In International conference on computer vision.","DOI":"10.1109\/ICCV.2017.148"},{"issue":"2","key":"10.1016\/j.neunet.2023.01.014_b130","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1037\/0033-295X.97.2.285","article-title":"Connectionist models of recognition memory: Constraints imposed by learning and forgetting functions","volume":"97","author":"Ratcliff","year":"1990","journal-title":"Psychological Review"},{"key":"10.1016\/j.neunet.2023.01.014_b131","doi-asserted-by":"crossref","unstructured":"Rebuffi,\u00a0S. A., Kolesnikov,\u00a0A., Sperl,\u00a0G., & Lampert,\u00a0C. H. (2017). iCaRL: Incremental classifier and representation learning. In Computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2017.587"},{"issue":"2","key":"10.1016\/j.neunet.2023.01.014_b132","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1080\/09540099550039318","article-title":"Catastrophic forgetting, rehearsal and pseudorehearsal","volume":"7","author":"Robins","year":"1995","journal-title":"Connection Science"},{"key":"10.1016\/j.neunet.2023.01.014_b133","unstructured":"Rolnick,\u00a0D., Ahuja,\u00a0A., Schwarz,\u00a0J., Lillicrap,\u00a0T. P., & Wayne,\u00a0G. (2018). Experience Replay for Continual Learning. In Neural information processing systems."},{"key":"10.1016\/j.neunet.2023.01.014_b134","unstructured":"Roy,\u00a0N., & McCallum,\u00a0A. (2001). Toward optimal active learning through monte carlo estimation of error reduction. In Proceedings of the international conference on machine learning (pp. 441\u2013448)."},{"key":"10.1016\/j.neunet.2023.01.014_b135","series-title":"An overview of multi-task learning in deep neural networks","author":"Ruder","year":"2017"},{"issue":"3","key":"10.1016\/j.neunet.2023.01.014_b136","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"ImageNet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"International Journal of Computer Vision (IJCV)"},{"key":"10.1016\/j.neunet.2023.01.014_b137","series-title":"Progressive neural networks","author":"Rusu","year":"2016"},{"key":"10.1016\/j.neunet.2023.01.014_b138","series-title":"On-line learning in neural networks","year":"1999"},{"key":"10.1016\/j.neunet.2023.01.014_b139","doi-asserted-by":"crossref","unstructured":"Sahoo,\u00a0D., Pham,\u00a0Q., Lu,\u00a0J., & Hoi,\u00a0S. C. H. (2018). Online deep learning: Learning deep neural networks on the fly. In International joint conference on artificial intelligence (pp. 2660\u20132666).","DOI":"10.24963\/ijcai.2018\/369"},{"issue":"2","key":"10.1016\/j.neunet.2023.01.014_b140","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1023\/A:1022648800760","article-title":"The strength of weak learnability","volume":"5","author":"Schapire","year":"1990","journal-title":"Machine Learning"},{"key":"10.1016\/j.neunet.2023.01.014_b141","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2014.2321392","article-title":"Probability models for open set recognition","author":"Scheirer","year":"2014","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"7","key":"10.1016\/j.neunet.2023.01.014_b142","doi-asserted-by":"crossref","first-page":"1757","DOI":"10.1109\/TPAMI.2012.256","article-title":"Towards open set recognition","volume":"35","author":"Scheirer","year":"2013","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"10.1016\/j.neunet.2023.01.014_b143","unstructured":"Sener,\u00a0O., & Savarese,\u00a0S. (2018). Active learning for convolutional neural networks: A core-set approach. In International conference on learning representations."},{"key":"10.1016\/j.neunet.2023.01.014_b144","unstructured":"Serra,\u00a0J., Suris,\u00a0D., Mir\u00f3n,\u00a0M., & Karatzoglou,\u00a0A. (2018). Overcoming Catastrophic forgetting with hard attention to the task. In International conference on machine learning."},{"key":"10.1016\/j.neunet.2023.01.014_b145","doi-asserted-by":"crossref","unstructured":"Settles,\u00a0B., & Craven,\u00a0M. (2008). An analysis of active learning strategies for sequence labeling tasks. In Empirical methods in natural language processing (pp. 1070\u20131079).","DOI":"10.3115\/1613715.1613855"},{"key":"10.1016\/j.neunet.2023.01.014_b146","doi-asserted-by":"crossref","unstructured":"Seung,\u00a0H. S., Opper,\u00a0M., & Sompolinsky,\u00a0H. (1992). Query by committee. In Proceedings of the fifth annual ACM workshop on computational learning theory (pp. 287\u2013294).","DOI":"10.1145\/130385.130417"},{"issue":"4","key":"10.1016\/j.neunet.2023.01.014_b147","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1002\/j.1538-7305.1948.tb00917.x","article-title":"A mathematical theory of communication","volume":"27","author":"Shannon","year":"1948","journal-title":"Bell System Technical Journal"},{"key":"10.1016\/j.neunet.2023.01.014_b148","unstructured":"Shin,\u00a0H., Lee,\u00a0J. K., Kim,\u00a0J. J., & Kim,\u00a0J. (2017). Continual Learning with Deep Generative Replay. In Neural information processing systems."},{"key":"10.1016\/j.neunet.2023.01.014_b149","unstructured":"Shui,\u00a0C., Zhou,\u00a0F., Gagn\u00e9,\u00a0C., & Wang,\u00a0B. (2020). Deep Active Learning: Unified and Principled Method for Query and Training. In AISTATS."},{"key":"10.1016\/j.neunet.2023.01.014_b150","doi-asserted-by":"crossref","unstructured":"Sinha,\u00a0S., Ebrahimi,\u00a0S., & Darrell,\u00a0T. (2019). Variational adversarial active learning. In International conference on computer vision.","DOI":"10.1109\/ICCV.2019.00607"},{"key":"10.1016\/j.neunet.2023.01.014_b151","article-title":"Towards training recurrent neural networks for lifelong learning","author":"Sodhani","year":"2019","journal-title":"Neural Computation"},{"key":"10.1016\/j.neunet.2023.01.014_b152","unstructured":"Srinivasan,\u00a0T., Chang,\u00a0T. Y., Pinto\u00a0Alva,\u00a0L. L., Chochlakis,\u00a0G., Rostami,\u00a0M., & Thomason,\u00a0J. (2022). CLiMB: A Continual Learning Benchmark for Vision-and-Language Tasks. In Neural information processing systems (NeurIPS), dataset and benchmarks track."},{"key":"10.1016\/j.neunet.2023.01.014_b153","first-page":"1929","article-title":"Dropout : A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"Journal of Machine Learning Research (JMRL)"},{"key":"10.1016\/j.neunet.2023.01.014_b154","series-title":"Neural networks. EURASIP 1990","article-title":"Rule-injection hints as a means of improving network performance and learning time","volume":"vol. 412","author":"Suddarth","year":"1990"},{"key":"10.1016\/j.neunet.2023.01.014_b155","series-title":"Explanation-based neural network learning - a lifelong learning approach","author":"Thrun","year":"1996"},{"key":"10.1016\/j.neunet.2023.01.014_b156","article-title":"Is learning the n-th thing any easier than learning the first?","author":"Thrun","year":"1996","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2023.01.014_b157","article-title":"Support vector machine active learning with applications to text classification","author":"Tong","year":"2001","journal-title":"Journal of Machine Learning Research (JMLR)"},{"key":"10.1016\/j.neunet.2023.01.014_b158","unstructured":"Tran,\u00a0T., Do,\u00a0T. T., Reid,\u00a0I., & Carneiro,\u00a0G. (2019). Bayesian generative active deep learning. In International conference on machine learning."},{"key":"10.1016\/j.neunet.2023.01.014_b159","first-page":"363","article-title":"Core vector machines: Fast SVM training on very large data sets","volume":"6","author":"Tsang","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"10.1016\/j.neunet.2023.01.014_b160","series-title":"Adaptation and learning in automatic systems","author":"Tsypkin","year":"1971"},{"issue":"8 MAR","key":"10.1016\/j.neunet.2023.01.014_b161","first-page":"1","article-title":"Functional neurogenesis in the adult hippocampus: Then and now","volume":"8","author":"Vadodaria","year":"2014","journal-title":"Frontiers in Neuroscience"},{"key":"10.1016\/j.neunet.2023.01.014_b162","series-title":"Generative replay with feedback connections as a general strategy for continual learning","author":"van de Ven","year":"2018"},{"key":"10.1016\/j.neunet.2023.01.014_b163","series-title":"Estimation of dependences based on empirical data","author":"Vapnik","year":"1982"},{"key":"10.1016\/j.neunet.2023.01.014_b164","article-title":"Generalizing from a few examples: A survey on few-shot learning","author":"Wang","year":"2020","journal-title":"ACM Computing Surveys"},{"issue":"1","key":"10.1016\/j.neunet.2023.01.014_b165","doi-asserted-by":"crossref","DOI":"10.1186\/s40537-016-0043-6","article-title":"A survey of transfer learning","volume":"3","author":"Weiss","year":"2016","journal-title":"Journal of Big Data"},{"key":"10.1016\/j.neunet.2023.01.014_b166","doi-asserted-by":"crossref","unstructured":"Welling,\u00a0M. (2009). Herding dynamical weights to learn. In International conference on machine learning (pp. 1121\u20131128).","DOI":"10.1145\/1553374.1553517"},{"key":"10.1016\/j.neunet.2023.01.014_b167","doi-asserted-by":"crossref","unstructured":"Weston,\u00a0J., Collobert,\u00a0R., Sinz,\u00a0F., Bottou,\u00a0L., & Vapnik,\u00a0V. (2006). Inference with the Universum. In International conference on machine learning.","DOI":"10.1145\/1143844.1143971"},{"key":"10.1016\/j.neunet.2023.01.014_b168","doi-asserted-by":"crossref","unstructured":"Wu,\u00a0Y., Chen,\u00a0Y., Wang,\u00a0L., Ye,\u00a0Y., Liu,\u00a0Z., Guo,\u00a0Y., et al. (2019). Large Scale Incremental Learning. In Computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2019.00046"},{"key":"10.1016\/j.neunet.2023.01.014_b169","unstructured":"Wu,\u00a0C., Herranz,\u00a0L., Liu,\u00a0X., Wang,\u00a0Y., van de Weijer,\u00a0J., & Raducanu,\u00a0B. (2018). Memory Replay GANs: learning to generate images from new categories without forgetting. In Neural information processing systems."},{"key":"10.1016\/j.neunet.2023.01.014_b170","doi-asserted-by":"crossref","unstructured":"Xiang,\u00a0Y., Fu,\u00a0Y., Ji,\u00a0P., & Huang,\u00a0H. (2019). Incremental Learning Using Conditional Adversarial Networks. In International conference on computer vision.","DOI":"10.1109\/ICCV.2019.00672"},{"key":"10.1016\/j.neunet.2023.01.014_b171","series-title":"Noise or signal: The role of image backgrounds in object recognition","author":"Xiao","year":"2020"},{"key":"10.1016\/j.neunet.2023.01.014_b172","unstructured":"Xu,\u00a0J., & Zhu,\u00a0Z. (2018). Reinforced continual learning. In Neural information processing systems."},{"key":"10.1016\/j.neunet.2023.01.014_b173","unstructured":"Yao,\u00a0H., Choi,\u00a0C., Lee,\u00a0Y., Koh,\u00a0P., & Finn,\u00a0C. (2022). Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time. In Neural information processing systems (NeurIPS), dataset and benchmarks track."},{"key":"10.1016\/j.neunet.2023.01.014_b174","unstructured":"Yoon,\u00a0J., Yang,\u00a0E., Lee,\u00a0J., & Hwang,\u00a0S. J. (2018). Lifelong Learning with Dynamically Expandable Networks. In International conference on learning representations."},{"key":"10.1016\/j.neunet.2023.01.014_b175","doi-asserted-by":"crossref","unstructured":"Yoshihashi,\u00a0R., Shao,\u00a0W., Kawakami,\u00a0R., You,\u00a0S., Iida,\u00a0M., & Naemura,\u00a0T. (2019). Classification-Reconstruction Learning for Open-Set Recognition. In Computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2019.00414"},{"key":"10.1016\/j.neunet.2023.01.014_b176","unstructured":"Yosinski,\u00a0J., Clune,\u00a0J., Bengio,\u00a0Y., & Lipson,\u00a0H. (2014). How transferable are features in deep neural networks?. In Neural information processing systems."},{"key":"10.1016\/j.neunet.2023.01.014_b177","doi-asserted-by":"crossref","unstructured":"Yu,\u00a0Q., & Aizawa,\u00a0K. (2019). Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancy. In International conference on computer vision.","DOI":"10.1109\/ICCV.2019.00961"},{"key":"10.1016\/j.neunet.2023.01.014_b178","doi-asserted-by":"crossref","unstructured":"Zagoruyko,\u00a0S., & Komodakis,\u00a0N. (2016). Wide Residual Networks. In British machine vision conference.","DOI":"10.5244\/C.30.87"},{"key":"10.1016\/j.neunet.2023.01.014_b179","unstructured":"Zenke,\u00a0F., Poole,\u00a0B., & Ganguli,\u00a0S. (2017). Continual Learning Through Synaptic Intelligence. In International conference on machine learning, vol. 70 (pp. 3987\u20133995)."},{"key":"10.1016\/j.neunet.2023.01.014_b180","doi-asserted-by":"crossref","unstructured":"Zhai,\u00a0M., Chen,\u00a0L., Tung,\u00a0F., He,\u00a0J., Nawhal,\u00a0M., & Mori,\u00a0G. (2019). Lifelong GAN: Continual Learning for Conditional Image Generation. In International conference on computer vision.","DOI":"10.1109\/ICCV.2019.00285"},{"key":"10.1016\/j.neunet.2023.01.014_b181","unstructured":"Zhang,\u00a0T., & Oles,\u00a0F. J. (2000). A Probability Analysis on the Value of Unlabelled Data for Classification Problems. In International conference on machine learning."},{"key":"10.1016\/j.neunet.2023.01.014_b182","unstructured":"Zhou,\u00a0G., Sohn,\u00a0K., & Lee,\u00a0H. (2012). Online Incremental Feature Learning with Denoising Autoencoders. In International conference on artificial intelligence and statistics, vol. 22 (pp. 1453\u20131461)."},{"key":"10.1016\/j.neunet.2023.01.014_b183","unstructured":"Zhu,\u00a0J. J., & Bento,\u00a0J. (2017). Generative Adversarial Active Learning. In NeurIPS workshop on teaching machines, robots, and humans."},{"key":"10.1016\/j.neunet.2023.01.014_b184","doi-asserted-by":"crossref","unstructured":"Zhuang,\u00a0C., Xiang,\u00a0V., Bai,\u00a0Y., Jia,\u00a0X., Turk-Browne,\u00a0N., Norman,\u00a0K., et al. (2022). How Well Do Unsupervised Learning Algorithms Model Human Real-time and Life-long Learning?. In Neural information processing systems (NeurIPS), dataset and benchmarks track.","DOI":"10.32470\/CCN.2022.1155-0"},{"key":"10.1016\/j.neunet.2023.01.014_b185","unstructured":"Zinkevich,\u00a0M. (2003). Online Convex Programming and Generalized Infinitesimal Gradient Ascent. In International conference on machine learning."}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S089360802300014X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S089360802300014X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T02:13:22Z","timestamp":1760235202000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S089360802300014X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3]]},"references-count":185,"alternative-id":["S089360802300014X"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2023.01.014","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2023,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A wholistic view of continual learning with deep neural networks: Forgotten lessons and the bridge to active and open world learning","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2023.01.014","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2023 The Author(s). Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}]}}