{"type":"ScholarlyArticle","title":"Cognitively Inspired Learning of Incremental Drifting Concepts","authors":[{"name":"Mohammad Rostami","slug":"mohammad-rostami","given":"Mohammad","family":"Rostami","affiliation":"University of Southern California"},{"name":"Aram Galstyan","slug":"aram-galstyan","given":"Aram","family":"Galstyan","affiliation":"University of Southern California"}],"abstract":"Humans continually expand their learned knowledge to new domains and learn new concepts without any interference with past learned experiences. In contrast, machine learning models perform poorly in a continual learning setting, where input data distribution changes over time. Inspired by the nervous system learning mechanisms, we develop a computational model that enables a deep neural network to learn new concepts and expand its learned knowledge to new domains incrementally in a continual learning setting. We rely on the Parallel Distributed Processing theory to encode abstract concepts in an embedding space in terms of a multimodal distribution. This embedding space is modeled by internal data representations in a hidden network layer. We also leverage the Complementary Learning Systems theory to equip the model with a memory mechanism to overcome catastrophic forgetting through implementing pseudo-rehearsal. Our model can generate pseudo-data points for experience replay and accumulate new experiences to past learned experiences without causing cross-task interference.","doi":"10.24963/ijcai.2023/341","url":"https://ijcai.org/proceedings/2023/341","pdf":"https://ijcai.org/proceedings/2023/0341.pdf","markdown":"https://ijcai.org/proceedings/2023/341.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/341","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Humans and AI","track":"Main Track","number":341,"pages":{"first":3058,"last":3066},"keywords":["Humans and AI: HAI: Brain sciences","Humans and AI: HAI: Cognitive modeling","Humans and AI: HAI: Cognitive systems"],"videos":[],"references":[{"position":1,"raw":"[Aljundi et al., 2019] Rahaf Aljundi, Min Lin, Baptiste Gou- jaud, and Yoshua Bengio. Gradient based sample selection for online continual learning. In Advances in Neural Infor- mation Processing Systems, pages 11816-11825, 2019.","title":"Gradient based sample selection for online continual learning","authors":"Rahaf Aljundi, Min Lin, Baptiste Goujaud, Yoshua Bengio","year":"2019","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bonneel et al., 2015] Nicolas Bonneel, Julien Rabin, Gabriel Peyré, and Hanspeter Pfister. Sliced and radon wasserstein barycenters of measures. Journal of Math. Imag. and Vision, 51(1):22-45, 2015.","title":"Sliced and radon wasserstein barycenters of measures","authors":"Nicolas Bonneel, Julien Rabin, Gabriel Peyré, Hanspeter Pfister","year":"2015","venue":"Journal of Math. Imag. and Vision","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chen and Liu, 2016] Zhiyuan Chen and Bing Liu. Lifelong machine learning. Synthesis Lectures on Artificial Intelli- gence and Machine Learning, 10(3):1-145, 2016.","title":"Lifelong machine learning","authors":"Chen, Liu, Zhiyuan Chen, Bing Liu","year":"2016","venue":"Synthesis Lectures on Artificial Intelligence and Machine Learning","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Courty et al., 2017] Nicolas Courty, Rémi Flamary, Devis Tuia, and Alain Rakotomamonjy. Optimal transport for domain adaptation. IEEE TPAMI, 39(9):1853-1865, 2017.","title":"Optimal transport for domain adaptation","authors":"Nicolas Courty, Rémi Flamary, Devis Tuia, Alain Rakotomamonjy","year":"2017","venue":"IEEE TPAMI","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[French, 1991] Robert M French. Using semi-distributed representations to overcome catastrophic forgetting in con- nectionist networks. In Proceedings of the 13th annual cognitive science society conference, volume 1, pages 173-178, 1991.","title":"Using semi-distributed representations to overcome catastrophic forgetting in connectionist networks","authors":"M Robert, French","year":"1991","venue":"Proceedings of the 13th annual cognitive science society conference","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[French, 1999] Robert M French. Catastrophic forgetting in connectionist networks. Trends in Cog. Sciences, 3(4):128-135, 1999.","title":"Catastrophic forgetting in connectionist networks","authors":"M Robert, French","year":"1999","venue":"Trends in Cog. Sciences","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Gama et al., 2014] João Gama, Indrė Žliobaitė, Albert Bifet, Mykola Pechenizkiy, and Abdelhamid Bouchachia. A survey on concept drift adaptation. CSUR, 46(4):1-37, 2014.","title":"A survey on concept drift adaptation","authors":"João Gama, Indrė Žliobaitė, Albert Bifet, Mykola Pechenizkiy, Abdelhamid Bouchachia","year":"2014","venue":"CSUR","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Gennari et al., 1989] John H Gennari, Pat Langley, and Doug Fisher. Models of incremental concept formation. Artificial intelligence, 40(1-3):11-61, 1989.","title":"Models of incremental concept formation","authors":"Pat John H Gennari, Doug Langley, Fisher","year":"1989","venue":"Artificial intelligence","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[He and Jaeger, 2018] Xu He and Herbert Jaeger. Overcom- ing catastrophic interference using conceptor-aided back- propagation. In International Conference on Learning Representations, 2018.","title":"Overcoming catastrophic interference using conceptor-aided backpropagation","authors":"Xu He, Herbert Jaeger","year":"2018","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Jiang and Conrath, 1997] Jay J Jiang and David W Conrath. Semantic similarity based on corpus statistics and lexical taxonomy. In Proceedings of the 10th Research on Compu- tational Linguistics International Conference, pages 19- -33, 1997.","title":"Semantic similarity based on corpus statistics and lexical taxonomy","authors":"J Jay, David W Jiang, Conrath","year":"1997","venue":"Proceedings of the 10th Research on Computational Linguistics International Conference","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kirkpatrick et al., 2017] James Kirkpatrick, Razvan Pas- canu, Neil Rabinowitz, and Others. Overcoming catas- trophic forgetting in neural networks. Proceedings of the national academy of sciences, 114(13):3521-3526, 2017.","title":"Overcoming catastrophic forgetting in neural networks","authors":"James Kirkpatrick, Razvan Pascanu, Neil Rabinowitz, Others","year":"2017","venue":"Proceedings of the national academy of sciences","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Lake et al., 2015] Brenden M Lake, Ruslan Salakhutdinov, and Joshua B Tenenbaum. Human-level concept learn- ing through probabilistic program induction. Science, 350(6266):1332-1338, 2015.","title":"Human-level concept learning through probabilistic program induction","authors":"Ruslan Brenden M Lake, Joshua B Salakhutdinov, Tenenbaum","year":"2015","venue":"Science","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Lamprecht and LeDoux, 2004] Raphael Lamprecht and Joseph LeDoux. Structural plasticity and memory. Nature Reviews Neuroscience, 5(1):45, 2004.","title":"Structural plasticity and memory","authors":"Ledoux Lamprecht, Raphael Lamprecht, Joseph Ledoux","year":"2004","venue":"Nature Reviews Neuroscience","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Lee et al., 2017] Sang-Woo Lee, Jin-Hwa Kim, Jaehyun Jun, Jung-Woo Ha, and Byoung-Tak Zhang. Overcom- ing catastrophic forgetting by incremental moment match- ing. In Advances in neural information processing sys- tems, pages 4652-4662, 2017.","title":"Overcoming catastrophic forgetting by incremental moment matching","authors":"Sang-Woo Lee, Jin-Hwa Kim, Jaehyun Jun, Jung-Woo Ha, Byoung-Tak Zhang","year":"2017","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Li and Hoiem, 2018] Zhizhong Li and Derek Hoiem. Learning without forgetting. IEEE Transactions on Pat- tern Analysis and Machine Intelligence, 40(12):2935- 2947, 2018.","title":"Learning without forgetting","authors":"Hoiem ; Li, Zhizhong Li, Derek Hoiem","year":"2018","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Lopez-Paz and Ranzato, 2017] David Lopez-Paz and Marc'Aurelio Ranzato. Gradient episodic memory for continual learning. In Advances in neural information processing systems, pages 6467-6476, 2017.","title":"Gradient episodic memory for continual learning","authors":"David Lopez, - Paz, Marc'aurelio Ranzato","year":"2017","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[McClelland and Rogers, 2003] James L McClelland and Timothy T Rogers. The parallel distributed processing approach to semantic cognition. Nature reviews Neuro., 4(4):310-322, 2003.","title":"The parallel distributed processing approach to semantic cognition","authors":"L James, Timothy T Mcclelland, Rogers","year":"2003","venue":"Nature reviews Neuro","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[McClelland et al., 1986] James L McClelland, David E Rumelhart, PDP Research Group, et al. Parallel distributed processing. Explorations in the Microstructure of Cogni- tion, 2:216-271, 1986.","title":"Parallel distributed processing","authors":"David E James L Mcclelland, Pdp Rumelhart, Research Group","year":"1986","venue":"Explorations in the Microstructure of Cognition","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[McClelland et al., 1995] James L McClelland, Bruce L Mc- Naughton, and Randall C O'Reilly. Why there are com- plementary learning systems in the hippocampus and neo- cortex: Insights from the successes and failures of con- nectionist models of learning and memory. Psychological Review, 102(3):419, 1995.","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","authors":"Bruce L James L Mcclelland, Randall C O' Mc-Naughton, Reilly","year":"1995","venue":"Psychological Review","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[McInnes et al., 2018] Leland McInnes, John Healy, and James Melville. Umap: Uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426, 2018.","title":"Umap: Uniform manifold approximation and projection for dimension reduction","authors":"Leland Mcinnes, John Healy, James Melville","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Morgenstern et al., 2014] Yaniv Morgenstern, Mohammad Rostami, and Dale Purves. Properties of artificial net- works evolved to contend with natural spectra. Proceed- ings of the National Academy of Sciences, 111(Supple- ment 3):10868-10872, 2014.","title":"Properties of artificial networks evolved to contend with natural spectra","authors":"Yaniv Morgenstern, Mohammad Rostami, Dale Purves","year":"2014","venue":"Proceedings of the National Academy of Sciences","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Rannen et al., 2017] Amal Rannen, Rahaf Aljundi, Matthew B Blaschko, and Tinne Tuytelaars. Encoder based lifelong learning. In Proceedings of the IEEE International Conference on Computer Vision, pages 1320-1328, 2017.","title":"Encoder based lifelong learning","authors":"Amal Rannen, Rahaf Aljundi, Matthew B Blaschko, Tinne Tuytelaars","year":"2017","venue":"Proceedings of the IEEE International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Rasch and Born, 2013] Björn Rasch and Jan Born. About sleep's role in memory. Physiological Reviews, 93(2):681- 766, 2013.","title":"About sleep's role in memory","authors":"Born Rasch, Björn Rasch, Jan Born","year":"2013","venue":"Physiological Reviews","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Rebuffi et al., 2017] Sylvestre-Alvise Rebuffi, Alexander Kolesnikov, Georg Sperl, and Christoph H Lampert. icarl: Incremental classifier and representation learning. In Pro- ceedings of the IEEE conference on Computer Vision and Pattern Recognition, pages 2001-2010, 2017.","title":"icarl: Incremental classifier and representation learning","authors":"Sylvestre-Alvise, Alexander Rebuffi, Georg Kolesnikov, Christoph H Sperl, Lampert","year":"2017","venue":"Proceedings of the IEEE conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Robins, 1995] Anthony Robins. Catastrophic forgetting, rehearsal and pseudorehearsal. Connection Science, 7(2):123-146, 1995.","title":"Catastrophic forgetting, rehearsal and pseudorehearsal","authors":"Anthony Robins","year":"1995","venue":"Connection Science","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Rostami and Galstyan, 2023] Mohammad Rostami and Aram Galstyan. Overcoming concept shift in do- mainaware settings through consolidated internal distributions. In Proceedings of the AAAI conference on artificial intelligence, volume 1, 2023.","title":"Overcoming concept shift in domainaware settings through consolidated internal distributions","authors":"Galstyan Rostami, Mohammad Rostami, Aram Galstyan","year":"2023","venue":"Proceedings of the AAAI conference on artificial intelligence","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Rostami et al., 2018] Mohammad Rostami, David Huber, and Tsai-Ching Lu. A crowdsourcing triage algorithm for geopolitical event forecasting. In Proceedings of the 12th ACM Conference on Recommender Systems, pages 377- 381, 2018.","title":"A crowdsourcing triage algorithm for geopolitical event forecasting","authors":"Mohammad Rostami, David Huber, Tsai-Ching Lu","year":"2018","venue":"Proceedings of the 12th ACM Conference on Recommender Systems","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Rostami et al., 2019] Mohammad Rostami, Soheil Kolouri, and Praveen Pilly. Complementary learning for overcom- ing catastrophic forgetting using experience replay. In IJ- CAI, 2019.","title":"Complementary learning for overcoming catastrophic forgetting using experience replay","authors":"Mohammad Rostami, Soheil Kolouri, Praveen Pilly","year":"2019","venue":"IJ-CAI","doi":null,"url":null,"internal_url":"/proceedings/2019/463"},{"position":29,"raw":"[Rostami et al., 2020a] Mohammad Rostami, David Isele, and Eric Eaton. Using task descriptions in lifelong machine learning for improved performance and zero- shot transfer. Journal of Artificial Intelligence Research, 67:673-704, 2020.","title":"Using task descriptions in lifelong machine learning for improved performance and zeroshot transfer","authors":"Rostami","year":"2020","venue":"Journal of Artificial Intelligence Research","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Rostami et al., 2020b] Mohammad Rostami, Soheil Kolouri, Praveen Pilly, and James McClelland. Generative continual concept learning. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 5545-5552, 2020.","title":"Generative continual concept learning","authors":"Rostami","year":"2020","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Rostami, 2021a] Mohammad Rostami. Lifelong domain adaptation via consolidated internal distribution. In Pro- ceedings of the 2021 NeurIPS Conference, 2021.","title":"Lifelong domain adaptation via consolidated internal distribution","authors":"Mohammad Rostami, Rostami","year":"2021","venue":"Proceedings of the 2021 NeurIPS Conference","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Rostami, 2021b] Mohammad Rostami. Transfer Learning Through Embedding Spaces. CRC Press, 2021.","title":"Transfer Learning Through Embedding Spaces","authors":"Rostami","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Roy et al., 2020] Deboleena Roy, Priyadarshini Panda, and Kaushik Roy. Tree-cnn: a hierarchical deep cnn for incre- mental learning. Neural Networks, 121:148-160, 2020.","title":"Deboleena Roy, Priyadarshini Panda, and Kaushik Roy. Tree-cnn: a hierarchical deep cnn for incremental learning","authors":"Roy","year":"2020","venue":"Neural Networks","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Sarwar et al., 2019] Syed Shakib Sarwar, Aayush Ankit, and Kaushik Roy. Incremental learning in deep convolu- tional neural networks using partial network sharing. IEEE Access, 2019.","title":"Incremental learning in deep convolutional neural networks using partial network sharing","authors":"Syed Shakib Sarwar, Aayush Ankit, Kaushik Roy","year":"2019","venue":"IEEE Access","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Saxe et al., 2019] Andrew M Saxe, James L McClelland, and Surya Ganguli. A mathematical theory of semantic development in deep neural networks. Proceedings of the National Academy of Sciences, page 201820226, 2019.","title":"A mathematical theory of semantic development in deep neural networks","authors":"James L Andrew M Saxe, Surya Mcclelland, Ganguli","year":"2019","venue":"Proceedings of the National Academy of Sciences","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Schaul et al., 2016] Tom Schaul, John Quan, Ioannis Antonoglou, and David Silver. Prioritized experience re- play. In IJCLR, 2016.","title":"Prioritized experience replay","authors":"Tom Schaul, John Quan, Ioannis Antonoglou, David Silver","year":"2016","venue":"IJCLR","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Shin et al., 2017] Hanul Shin, Jung Kwon Lee, Jaehong Kim, and Jiwon Kim. Continual learning with deep gener- ative replay. In NeurIPS, pages 2990-2999, 2017.","title":"Continual learning with deep generative replay","authors":"Hanul Shin, Jung Kwon Lee, Jaehong Kim, Jiwon Kim","year":"2017","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Stan and Rostami, 2021] Serban Stan and Mohammad Ros- tami. Unsupervised model adaptation for continual seman- tic segmentation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 2593-2601, 2021.","title":"Unsupervised model adaptation for continual semantic segmentation","authors":"Stan, Rostami","year":"2021","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Widmer and Kubat, 1996] Gerhard Widmer and Miroslav Kubat. Learning in the presence of concept drift and hid- den contexts. Machine learning, 23(1):69-101, 1996.","title":"Learning in the presence of concept drift and hidden contexts","authors":"Kubat Widmer, Gerhard Widmer, Miroslav Kubat","year":"1996","venue":"Machine learning","doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Wu et al., 2018] Chenshen Wu, Luis Herranz, Xialei Liu, Joost van de Weijer, Bogdan Raducanu, et al. Memory replay gans: Learning to generate new categories without forgetting. In NeurIPS, pages 5962-5972, 2018.","title":"Memory replay gans: Learning to generate new categories without forgetting","authors":"Wu","year":"2018","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Zeng et al., 2019] Guanxiong Zeng, Yang Chen, Bo Cui, and Shan Yu. Continual learning of context-dependent processing in neural networks. Nature Machine Intelli- gence, 1(8):364-372, 2019.","title":"Continual learning of context-dependent processing in neural networks","authors":"Guanxiong Zeng, Yang Chen, Bo Cui, Shan Yu","year":"2019","venue":"Nature Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Zenke et al., 2017] Friedemann Zenke, Wulfram Gerstner, and Surya Ganguli. The temporal paradox of hebbian learning and homeostatic plasticity. Curr. opinion in neuro., 43:166-176, 2017.","title":"The temporal paradox of hebbian learning and homeostatic plasticity","authors":"Friedemann Zenke, Wulfram Gerstner, Surya Ganguli","year":"2017","venue":"Curr. opinion in neuro","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}