{"type":"ScholarlyArticle","title":"Self-Organizing Incremental Neural Networks for Continual Learning","authors":[{"name":"Chayut Wiwatcharakoses","slug":"chayut-wiwatcharakoses","given":"Chayut","family":"Wiwatcharakoses","affiliation":"Data Science Laboratory , School of Engineering , Tokyo Institute of Technology , Japan"},{"name":"Daniel Berrar","slug":"daniel-berrar","given":"Daniel","family":"Berrar","affiliation":"Data Science Laboratory , School of Engineering , Tokyo Institute of Technology , Japan"}],"abstract":"Continual learning systems can adapt to new tasks, changes in data distributions, and new information that becomes incrementally available over time. The key challenge for such systems is how to mitigate catastrophic forgetting, i.e., how to prevent the loss of previously learned knowledge when new tasks need to be solved. In our research, we investigate self-organizing incremental neural networks (SOINN) for continual learning from both stationary and non-stationary data. We have developed a new algorithm, SOINN+, that learns to forget irrelevant nodes and edges and is robust to noise.","doi":"10.24963/ijcai.2019/927","url":"https://ijcai.org/proceedings/2019/927","pdf":"https://ijcai.org/proceedings/2019/0927.pdf","markdown":"https://ijcai.org/proceedings/2019/927.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/927","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Doctoral Consortium","track":"Doctoral Consortium","number":927,"pages":{"first":6476,"last":6477},"keywords":["Machine Learning: Transfer, Adaptation, Multi-task Learning","Machine Learning: Clustering","Machine Learning: Online Learning","Machine Learning: Unsupervised Learning"],"videos":[],"references":[{"position":1,"raw":"[Ditzler et al., 2015] Gregory Ditzler, Manuel Roveri, Ce- sare Alippi, and Robi Polikar. Learning in nonstationary environments: A survey. IEEE Computational Intelligence Magazine, 10(4):12-25, 2015.","title":"Learning in nonstationary environments: A survey","authors":"Gregory Ditzler, Manuel Roveri, Cesare Alippi, Robi Polikar","year":"2015","venue":"IEEE Computational Intelligence Magazine","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[McCloskey and Cohen, 1989] Michael McCloskey and Neal J. Cohen. Catastrophic interference in connec- tionist networks: the sequential learning problem. The Psychology of Learning and Motivation, 24:104-169, 1989.","title":"Catastrophic interference in connectionist networks: the sequential learning problem","authors":"Michael Mccloskey, Neal J Cohen","year":"1989","venue":"The Psychology of Learning and Motivation","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Okada et al., 2010] Shogo Okada, Yoichi Kobayashi, Satoshi Ishibashi, and Toyoaki Nishida. Incremental learning of gestures for human-robot interaction. AI & Society, 25(2):155-168, 2010.","title":"Incremental learning of gestures for human-robot interaction","authors":"Shogo Okada, Yoichi Kobayashi, Satoshi Ishibashi, Toyoaki Nishida","year":"2010","venue":"AI & Society","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Parisi et al., 2019] German I. Parisi, Ronald Kemker, Jose L. Part, Christopher Kanan, and Stefan Wermter. Continual lifelong learning with neural networks: A re- view. Neural Networks, 13:54-71, 2019.","title":"Continual lifelong learning with neural networks: A review","authors":"Parisi","year":"2019","venue":"Neural Networks","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Shen and Hasegawa, 2006] Furao Shen and Osamu Hasegawa. An incremental network for on-line unsu- pervised classification and topology learning. Neural Networks, 19(1):90-106, 2006.","title":"An incremental network for on-line unsupervised classification and topology learning","authors":"Hasegawa Shen, Furao Shen, Osamu Hasegawa","year":"2006","venue":"Neural Networks","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Shen and Hasegawa, 2008] Furao Shen and Osamu Hasegawa. A fast nearest neighbor classifier based on self-organizing incremental neural network. Neural Networks, 21(10):1537-1547, 2008.","title":"Furao Shen and Osamu Hasegawa. A fast nearest neighbor classifier based on self-organizing incremental neural network","authors":"Hasegawa Shen","year":"2008","venue":"Neural Networks","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}