{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T07:33:48Z","timestamp":1723016028697},"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":[[2020,7]]},"abstract":"<jats:p>By virtue of their expressive power, neural networks (NNs) are well suited to fitting large, complex datasets, yet they are also known to \n\nproduce similar predictions for points outside the training distribution.\n\nAs such, they are, like humans, under the influence of the Black Swan theory: models tend to be extremely \"surprised\" by rare events, leading to potentially disastrous consequences, while justifying these same events in hindsight.\n\nTo avoid this pitfall, we introduce DENN, an ensemble approach building a set of Diversely Extrapolated Neural Networks that fits the training data and is able to generalize more diversely when extrapolating to novel data points.\n\nThis leads DENN to output highly uncertain predictions for unexpected inputs.\n\nWe achieve this by adding a diversity term in the loss function used to train the model, computed at specific inputs.\n\nWe first illustrate the usefulness of the method on a low-dimensional regression problem. \n\nThen, we show how the loss can be adapted to tackle anomaly detection during classification, as well as safe imitation learning problems.<\/jats:p>","DOI":"10.24963\/ijcai.2020\/296","type":"proceedings-article","created":{"date-parts":[[2020,7,8]],"date-time":"2020-07-08T12:12:10Z","timestamp":1594210330000},"page":"2140-2147","source":"Crossref","is-referenced-by-count":6,"title":["Handling Black Swan Events in Deep Learning with Diversely Extrapolated Neural Networks"],"prefix":"10.24963","author":[{"given":"Maxime","family":"Wabartha","sequence":"first","affiliation":[{"name":"McGill University"},{"name":"Mila"}]},{"given":"Audrey","family":"Durand","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Laval"},{"name":"Mila"}]},{"given":"Vincent","family":"Fran\u00e7ois-Lavet","sequence":"additional","affiliation":[{"name":"Universit\u00e9 de Louvain"}]},{"given":"Joelle","family":"Pineau","sequence":"additional","affiliation":[{"name":"McGill University"},{"name":"Facebook AI Research"},{"name":"Mila"}]}],"member":"10584","event":{"number":"28","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-PRICAI-2020","name":"Twenty-Ninth International Joint Conference on Artificial Intelligence and Seventeenth Pacific Rim International Conference on Artificial Intelligence {IJCAI-PRICAI-20}","start":{"date-parts":[[2020,7,11]]},"theme":"Artificial Intelligence","location":"Yokohama, Japan","end":{"date-parts":[[2020,7,17]]}},"container-title":["Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2020,7,9]],"date-time":"2020-07-09T02:14:20Z","timestamp":1594260860000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2020\/296"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2020\/296","relation":{},"subject":[],"published":{"date-parts":[[2020,7]]}}}