{"type":"ScholarlyArticle","title":"Unsupervised Hierarchical Temporal Abstraction by Simultaneously Learning Expectations and Representations","authors":[{"name":"Katherine Metcalf","slug":"katherine-metcalf","given":"Katherine","family":"Metcalf","affiliation":"Computer Science Department , Indiana University"},{"name":"David Leake","slug":"david-leake","given":"David","family":"Leake","affiliation":"Computer Science Department , Indiana University"}],"abstract":"This paper presents ENHAnCE, an algorithm that simultaneously learns a predictive model of the input stream and generates representations of the concepts being observed. Following cognitively-inspired models of event segmentation, ENHAnCE uses expectation violations to identify boundaries between temporally extended patterns. It applies its expectation-driven process at multiple levels of temporal granularity to produce a hierarchy of predictive models that enable it to identify concepts at multiple levels of temporal abstraction. Evaluations show that the temporal abstraction hierarchies generated by ENHAnCE closely match hand-coded hierarchies for the test data streams. Given language data streams, ENHAnCE learns a hierarchy of predictive models that capture basic units of both spoken and written language: morphemes, lexemes, phonemes, syllables, and words.","doi":"10.24963/ijcai.2019/436","url":"https://ijcai.org/proceedings/2019/436","pdf":"https://ijcai.org/proceedings/2019/0436.pdf","markdown":"https://ijcai.org/proceedings/2019/436.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/436","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":"Machine Learning M-Z","track":"Main track","number":436,"pages":{"first":3144,"last":3150},"keywords":["Machine Learning: Online Learning","Humans and AI: Cognitive Modeling","Machine Learning: Time-series;Data Streams","Machine Learning: Reinforcement Learning"],"videos":[],"references":[{"position":1,"raw":"[Aha, 2018] David Aha. Goal reasoning: Foundations, emerging applications, and prospects. AI Magazine, 39(2):3-24, 2018.","title":"Goal reasoning: Foundations, emerging applications, and prospects","authors":"David Aha","year":"2018","venue":"AI Magazine","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bahdanau et al., 2016] Dzmitry Bahdanau, Jan Chorowski, Dmitriy Serdyuk, Philemon Brakel, and Yoshua Ben- gio. End-to-end attention-based large vocabulary speech recognition. In Acoustics, Speech and Signal Processing (ICASSP), 2016 IEEE International Conference on, pages 4945-4949. IEEE, 2016.","title":"End-to-end attention-based large vocabulary speech recognition","authors":"Dzmitry Bahdanau, Jan Chorowski, Dmitriy Serdyuk, Philemon Brakel, Yoshua Bengio","year":"2016","venue":"Acoustics, Speech and Signal Processing (ICASSP)","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chung et al., 2015] Junyoung Chung, Caglar Gulcehre, Kyunghyun Cho, and Yoshua Bengio. Gated feedback re- current neural networks. In International Conference on Machine Learning, pages 2067-2075, 2015.","title":"Gated feedback recurrent neural networks","authors":"Chung","year":"2015","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chung et al., 2016] Junyoung Chung, Sungjin Ahn, and Yoshua Bengio. Hierarchical multiscale recurrent neural networks. arXiv preprint arXiv:1609.01704, 2016.","title":"Hierarchical multiscale recurrent neural networks","authors":"Chung","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Cohen et al., 2007] Paul Cohen, Niall Adams, and Brent Heeringa. Voting experts: An unsupervised algorithm for segmenting sequences. Intelligent Data Analysis, 11(6):607-625, 2007.","title":"Voting experts: An unsupervised algorithm for segmenting sequences","authors":"Paul Cohen, Niall Adams, Brent Heeringa","year":"2007","venue":"Intelligent Data Analysis","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Dittenbach et al., 2000] Michael Dittenbach, Dieter Merkl, and Andreas Rauber. The growing hierarchical self- organizing map. In Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on, volume 6, pages 15-19. IEEE, 2000.","title":"The growing hierarchical selforganizing map","authors":"Michael Dittenbach, Dieter Merkl, Andreas Rauber","year":"2000","venue":"Proceedings of the IEEE-INNS-ENNS International Joint Conference on","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[El Hihi and Bengio, 1996] Salah El Hihi and Yoshua Ben- gio. Hierarchical recurrent neural networks for long-term dependencies. In Advances in neural information process- ing systems, pages 493-499, 1996.","title":"Salah El Hihi and Yoshua Bengio. Hierarchical recurrent neural networks for long-term dependencies","authors":"El Hihi, Bengio","year":"1996","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Franklin et al., 2019] Nicholas Franklin, Kenneth A Nor- man, Charan Ranganath, Jeffrey M Zacks, and Samuel J Gershman. Structured event memory: a neuro-symbolic model of event cognition. BioRxiv, page 541607, 2019.","title":"Structured event memory: a neuro-symbolic model of event cognition","authors":"Nicholas Franklin, Kenneth A Norman, Charan Ranganath, Jeffrey M Zacks, Samuel J Gershman","year":"2019","venue":"BioRxiv","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Goodfellow et al., 2013] Ian J Goodfellow, Mehdi Mirza, Da Xiao, Aaron Courville, and Yoshua Bengio. An em- pirical investigation of catastrophic forgetting in gradient- based neural networks. arXiv preprint arXiv:1312.6211, 2013.","title":"An empirical investigation of catastrophic forgetting in gradientbased neural networks","authors":"Ian J Goodfellow, Mehdi Mirza, Da Xiao, Aaron Courville, Yoshua Bengio","year":"2013","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Gumbsch et al., 2017] Christian Gumbsch, Sebastian Otte, and Martin V Butz. A computational model for the dy- namical learning of event taxonomies. In Proceedings of the 39th Annual Meeting of the Cognitive Science Society, pages 452-457, 2017.","title":"A computational model for the dynamical learning of event taxonomies","authors":"Gumbsch","year":"2017","venue":"Proceedings of the 39th Annual Meeting of the Cognitive Science Society","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Ha et al., 2015] JungWoo Ha, Kyung-Min Kim, and Byoung-Tak Zhang. Automated construction of visual- linguistic knowledge via concept learning from cartoon videos. In AAAI, pages 522-528, 2015.","title":"Automated construction of visuallinguistic knowledge via concept learning from cartoon videos","authors":"Ha","year":"2015","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[He et al., 2015] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Delving deep into rectifiers: Surpass- ing human-level performance on imagenet classification. In Proceedings of the IEEE international conference on computer vision, pages 1026-1034, 2015.","title":"Delving deep into rectifiers: Surpassing human-level performance on imagenet classification","authors":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun","year":"2015","venue":"Proceedings of the IEEE international conference on computer vision","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Koutnik et al., 2014] Jan Koutnik, Klaus Greff, Faustino Gomez, and Juergen Schmidhuber. A clockwork rnn. arXiv preprint arXiv:1402.3511, 2014.","title":"A clockwork rnn","authors":"Koutnik","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kurby and Zacks, 2008] Christopher A Kurby and Jef- frey M Zacks. Segmentation in the perception and memory of events. Trends in cognitive sciences, 12(2):72-79, 2008.","title":"Segmentation in the perception and memory of events","authors":"A Christopher, Jeffrey M Kurby, Zacks","year":"2008","venue":"Trends in cognitive sciences","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Lee et al., 2016] Sang-Woo Lee, Chung-Yeon Lee, Dong- Hyun Kwak, Jiwon Kim, Jeonghee Kim, and Byoung-Tak Zhang. Dual-memory deep learning architectures for life- long learning of everyday human behaviors. In IJCAI, pages 1669-1675, 2016.","title":"Dual-memory deep learning architectures for lifelong learning of everyday human behaviors","authors":"Sang-Woo Lee, Chung-Yeon Lee, Dong-Hyun Kwak, Jiwon Kim, Jeonghee Kim, Byoung-Tak Zhang","year":"2016","venue":"IJCAI","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Martin, 1989] Christopher Martin. Case-based parsing. In C. Riesbeck and R.C. Schank, editors, Inside Case-Based Reasoning, chapter 10, pages 319-352.","title":"Case-based parsing","authors":"Christopher Martin","year":null,"venue":"Inside Case-Based Reasoning","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"Lawrence Erl- baum, 1989. [Metcalf and Leake, 2017] Katherine Metcalf and David Leake. Modelling unsupervised event segmentation: Learning event boundaries from prediction errors. In Pro- ceedings of the 39th Annual Meeting of the Cognitive Sci- ence Society, 2017.","title":"Modelling unsupervised event segmentation: Learning event boundaries from prediction errors","authors":"Lawrence Erlbaum, ; Metcalf, Leake, Katherine Metcalf, David Leake","year":"1989","venue":"Proceedings of the 39th Annual Meeting of the Cognitive Science Society","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Miller and Stoytchev, 2008a] Matthew Miller and Alexan- der Stoytchev. Hierarchical voting experts: An unsuper- vised algorithm for hierarchical sequence segmentation. In Development and Learning, 2008. ICDL 2008. 7th IEEE International Conference on, pages 186-191. IEEE, 2008.","title":"Hierarchical voting experts: An unsupervised algorithm for hierarchical sequence segmentation","authors":"Stoytchev Miller","year":"2008","venue":"ICDL 2008. 7th IEEE International Conference on","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Miller and Stoytchev, 2008b] Matthew Miller and Alexan- der Stoytchev. Hierarchical voting experts: An unsuper- vised algorithm for segmenting hierarchically structured sequences. In AAAI, pages 1820-1821, 2008.","title":"Matthew Miller and Alexander Stoytchev. Hierarchical voting experts: An unsupervised algorithm for segmenting hierarchically structured sequences","authors":"Stoytchev Miller","year":"2008","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Mohseni-Kabir et al., 2018] Anahita Mohseni-Kabir, Changshuo Li, Victoria Wu, Daniel Miller, Benjamin Hy- lak, Sonia Chernova, Dmitry Berenson, Candace Sidner, and Charles Rich. Simultaneous learning of hierarchy and primitives for complex robot tasks. Autonomous Robots, pages 1-16, 2018.","title":"Simultaneous learning of hierarchy and primitives for complex robot tasks","authors":"Anahita Mohseni-Kabir, Changshuo Li, Victoria Wu, Daniel Miller, Benjamin Hylak, Sonia Chernova, Dmitry Berenson, Candace Sidner, Charles Rich","year":"2018","venue":"Autonomous Robots","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Newtson, 1973] Darren Newtson. Attribution and the unit of perception of ongoing behavior. Journal of Personality and Social Psychology, 28(1):28, 1973.","title":"Attribution and the unit of perception of ongoing behavior","authors":"Darren Newtson","year":"1973","venue":"Journal of Personality and Social Psychology","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Radvansky and Zacks, 2014] Gabriel A Radvansky and Jef- frey M Zacks. Event cognition. Oxford University Press, 2014.","title":"Event cognition","authors":"A Gabriel, Jeffrey M Radvansky, Zacks","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Reynolds et al., 2007] Jeremy R Reynolds, Jeffrey M Za- cks, and Todd S Braver. A computational model of event segmentation from perceptual prediction. Cognitive Sci- ence, 31(4):613-643, 2007.","title":"A computational model of event segmentation from perceptual prediction","authors":"Jeffrey M Jeremy R Reynolds, Todd S Zacks, Braver","year":"2007","venue":"Cognitive Science","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Saffran et al., 1996] Jenny R Saffran, Richard N Aslin, and Elissa L Newport. Statistical learning by 8-month-old in- fants. Science, 274(5294):1926-1928, 1996.","title":"Statistical learning by 8-month-old infants","authors":"Richard N Jenny R Saffran, Elissa L Aslin, Newport","year":"1996","venue":"Science","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Schank and Leake, 2002] Roger C. Schank and David Leake. Natural language understanding: Models of Roger Schank and his students. In Encyclopedia of Cognitive Sci- ence, pages 189-195. Nature Publishing Group, London, 2002.","title":"Natural language understanding: Models of Roger Schank and his students","authors":"Roger C Schank, David Leake","year":"2002","venue":"Encyclopedia of Cognitive Science","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Schmidhuber, 1992] Jürgen Schmidhuber. Learning com- plex, extended sequences using the principle of history compression. Neural Computation, 4(2):234-242, 1992.","title":"Learning complex, extended sequences using the principle of history compression","authors":"Jürgen Schmidhuber","year":"1992","venue":"Neural Computation","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Silver et al., 2017] David Silver, Julian Schrittwieser, Karen Simonyan, Ioannis Antonoglou, Aja Huang, Arthur Guez, Thomas Hubert, Lucas Baker, Matthew Lai, Adrian Bolton, et al. Mastering the game of go without human knowledge. Nature, 550(7676):354, 2017.","title":"Mastering the game of go without human knowledge","authors":"David Silver, Julian Schrittwieser, Karen Simonyan, Ioannis Antonoglou, Aja Huang, Arthur Guez, Thomas Hubert, Lucas Baker, Matthew Lai, Adrian Bolton","year":"2017","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Sutton and Barto, 2015] Richard S Sutton and Andrew G Barto. Reinforcement learning: An introduction, vol- ume 1. MIT press Cambridge, 2015.","title":"Reinforcement learning: An introduction","authors":"S Richard, Andrew G Sutton, Barto","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Zacks et al., 2007] Jeffrey M Zacks, Nicole K Speer, Khena M Swallow, Todd S Braver, and Jeremy R Reynolds. Event perception: a mind-brain perspective. Psychological bulletin, 133(2):273, 2007.","title":"Event perception: a mind-brain perspective","authors":"Nicole K Jeffrey M Zacks, Khena M Speer, Todd S Swallow, Jeremy R Braver, Reynolds","year":"2007","venue":"Psychological bulletin","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}