Zobrazeno 1 - 10
of 28
pro vyhledávání: '"Rishabh Iyer"'
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 36:10238-10246
With ever-increasing dataset sizes, subset selection techniques are becoming increasingly important for a plethora of tasks. It is often necessary to guide the subset selection to achieve certain desiderata, which includes focusing or targeting certa
Publikováno v:
IEEE Transactions on Information Theory. 68:752-781
Publikováno v:
Lecture Notes in Mechanical Engineering ISBN: 9783031288388
Supply chain issues arising from market turbulences force companies to find new solutions in the short term. Hence, deviations from the ideally designed business processes are inevitable, especially during production planning and control. These devia
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6aa1c86e6e74d4157330ddab4f26e240
https://doi.org/10.1007/978-3-031-28839-5_121
https://doi.org/10.1007/978-3-031-28839-5_121
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198380
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6ede41f739a7f7dc7324aafc2202d336
https://doi.org/10.1007/978-3-031-19839-7_1
https://doi.org/10.1007/978-3-031-19839-7_1
Publikováno v:
Medical Image Learning with Limited and Noisy Data ISBN: 9783031167591
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8996325373714423a858f7a176fa7c9b
https://doi.org/10.1007/978-3-031-16760-7_14
https://doi.org/10.1007/978-3-031-16760-7_14
Publikováno v:
Medical Image Learning with Limited and Noisy Data ISBN: 9783031167591
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::08f543e51abf9a4ef03e77c5a0377f2a
https://doi.org/10.1007/978-3-031-16760-7_12
https://doi.org/10.1007/978-3-031-16760-7_12
Publikováno v:
ISIT
Recently a class of generalized information measures was defined on sets of items parametrized by submodular functions. In this paper, we propose and study various notions of independence between sets with respect to such information measures, and co
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d95ded6f3950af2f6e3830f132029e6a
http://arxiv.org/abs/2108.03154
http://arxiv.org/abs/2108.03154
Publikováno v:
COMAD/CODS
Most learning algorithms are optimized with generalization and predictive performance as the goal. However, in most real-world machine learning applications, obtaining features at test time can incur a cost. For example, in clinical tasks, acquiring
Autor:
KrishnaTeja Killamsetty, Oishik Chatterjee, Rishabh Iyer, Ayush Maheshwari, Ganesh Ramakrishnan
Publikováno v:
ACL/IJCNLP (Findings)
The paradigm of data programming, which uses weak supervision in the form of rules/labelling functions, and semi-supervised learning, which augments small amounts of labelled data with a large unlabelled dataset, have shown great promise in several t
Publikováno v:
ACL/IJCNLP (Findings)
Recently, unsupervised parsing of syntactic trees has gained considerable attention. A prototypical approach to such unsupervised parsing employs reinforcement learning and auto-encoders. However, no mechanism ensures that the learnt model leverages