{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:07:06Z","timestamp":1765544826283},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,8]]},"abstract":"<jats:p>We first pose the Unsupervised Progressive Learning (UPL) problem: an online\n\nrepresentation learning problem in which the learner observes a non-stationary\n\nand unlabeled data stream, learning a growing number of features that persist\n\nover time even though the data is not stored or replayed. To solve the UPL\n\nproblem we propose the Self-Taught Associative Memory (STAM) architecture.\n\nLayered hierarchies of STAM modules learn based on a combination of online\n\nclustering, novelty detection, forgetting outliers, and storing only prototypical\n\nfeatures rather than specific examples. We evaluate STAM representations using\n\nclustering and classification tasks. While there are no existing learning scenarios\n\nthat are directly comparable to UPL, we compare the STAM architecture with two\n\nrecent continual learning models, Memory Aware Synapses (MAS) and Gradient\n\nEpisodic Memories (GEM), after adapting them in the UPL setting.<\/jats:p>","DOI":"10.24963\/ijcai.2021\/410","type":"proceedings-article","created":{"date-parts":[[2021,8,11]],"date-time":"2021-08-11T07:00:49Z","timestamp":1628665249000},"page":"2979-2987","source":"Crossref","is-referenced-by-count":16,"title":["Unsupervised Progressive Learning and the STAM Architecture"],"prefix":"10.24963","author":[{"given":"James","family":"Smith","sequence":"first","affiliation":[{"name":"Georgia Institute of Technology"}]},{"given":"Cameron","family":"Taylor","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}]},{"given":"Seth","family":"Baer","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}]},{"given":"Constantine","family":"Dovrolis","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}]}],"member":"10584","event":{"number":"30","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2021","name":"Thirtieth International Joint Conference on Artificial Intelligence {IJCAI-21}","start":{"date-parts":[[2021,8,19]]},"theme":"Artificial Intelligence","location":"Montreal, Canada","end":{"date-parts":[[2021,8,27]]}},"container-title":["Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2021,8,11]],"date-time":"2021-08-11T07:03:07Z","timestamp":1628665387000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2021\/410"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2021,8]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2021\/410","relation":{},"subject":[],"published":{"date-parts":[[2021,8]]}}}