Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Gondal, M. W."'
Autor:
Gondal, M. W., Rahaman, N., Joshi, S., Gehler, P., Bengio, Y., Francesco Locatello, Schölkopf, B.
Publikováno v:
Scopus-Elsevier
Advances in Neural Information Processing Systems 34
Advances in Neural Information Processing Systems 34
Modern neural network architectures can leverage large amounts of data to generalize well within the training distribution. However, they are less capable of systematic generalization to data drawn from unseen but related distributions, a feat that i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f08e2dc8b31f0d6b243567e9943ef85d
Autor:
Gondal, M. W., Wüthrich, M., Miladinovic, Ð., Francesco Locatello, Breidt, M., Volchkov, V., Akpo, J., Bachem, O., Schölkopf, B., Bauer, S.
Publikováno v:
Valentin Volchkov
Advances in Neural Information Processing Systems 32 (NeurIPS 2019)
Scopus-Elsevier
Advances in Neural Information Processing Systems 32 (NeurIPS 2019)
Scopus-Elsevier
Learning meaningful and compact representations with disentangled semantic aspects is considered to be of key importance in representation learning. Since real-world data is notoriously costly to collect, many recent state-of-the-art disentanglement
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7d339d7f7e0173aa399028a57bf0c5a1
https://papers.nips.cc/paper/9704-on-the-transfer-of-inductive-bias-from-simulation-to-the-real-world-a-new-disentanglement-dataset
https://papers.nips.cc/paper/9704-on-the-transfer-of-inductive-bias-from-simulation-to-the-real-world-a-new-disentanglement-dataset