Zobrazeno 1 - 10
of 55
pro vyhledávání: '"Louizos C"'
Autor:
Louizos, C.
In this thesis, we work towards improving two important aspects of deep neural networks via a probabilistic point of view; the uncertainty in their predictions and their efficiency as computational models. On the uncertainty side, we propose posterio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=narcis______::e3684c870216d049aa25f9ece8492eff
https://dare.uva.nl/personal/pure/en/publications/probabilistic-reasoning-for-uncertainty--compression-in-deep-learning(9eff2fb3-7c69-4a25-b883-7ade3fa556a4).html
https://dare.uva.nl/personal/pure/en/publications/probabilistic-reasoning-for-uncertainty--compression-in-deep-learning(9eff2fb3-7c69-4a25-b883-7ade3fa556a4).html
The importance of algorithmic fairness grows with the increasing impact machine learning has on people's lives. Recent work on fairness metrics shows the need for causal reasoning in fairness constraints. In this work, a practical method named FairTr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=narcis______::f9e40ab6d3936000af736b2a02a14c7a
https://dare.uva.nl/personal/pure/en/publications/improving-fair-predictions-using-variational-inference-in-causal-models(d79302a4-d9f9-433a-a823-2057bf1f5379).html
https://dare.uva.nl/personal/pure/en/publications/improving-fair-predictions-using-variational-inference-in-causal-models(d79302a4-d9f9-433a-a823-2057bf1f5379).html
Publikováno v:
ICLR 2019: International Conference on Learning Representations : New Orleans, Louisiana, United States, May 6-May 9, 2019
ICLR 2019
7th International Conference on Learning Representations, ICLR 2019, 7th International Conference on Learning Representations, ICLR 2019, 6 May 2019 through 9 May 2019
ICLR 2019
7th International Conference on Learning Representations, ICLR 2019, 7th International Conference on Learning Representations, ICLR 2019, 6 May 2019 through 9 May 2019
Neural network quantization has become an important research area due to its great impact on deployment of large models on resource constrained devices. In order to train networks that can be effectively discretized without loss of performance, we in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::86a484c75ba7e3d9742a7ca443f4e3b8
https://dare.uva.nl/personal/pure/en/publications/relaxed-quantization-for-discretized-neural-networks(c9c12a72-e6b1-47bd-a0c3-7add6bc68bf2).html
https://dare.uva.nl/personal/pure/en/publications/relaxed-quantization-for-discretized-neural-networks(c9c12a72-e6b1-47bd-a0c3-7add6bc68bf2).html
Publikováno v:
Deep Generative Models for Highly Structured Data, DGS@ICLR 2019 Workshop, 2019 Deep Generative Models for Highly Structured Data, DGS@ICLR 2019 Workshop, 6-May-19
We consider the problem of domain generalization, namely, how to learn representations given data from a set of domains that generalize to data from a previously unseen domain. We propose the Domain Invariant Variational Autoencoder (DIVA), a generat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ebb26fe6d2af4812b318cec10ac02216
Publikováno v:
International Journal of Impotence Research. Jul/Aug2014, Vol. 26 Issue 4, p146-150. 5p.
Autor:
Louizos, C., Shalit, U., Mooij, J., Sontag, D., Zemel, R., Welling, M., von Luxburg, U., Guyon, I., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S.V.N., Garnett, R.
Publikováno v:
31st Conference on Advances in Neural Information Processing Systems (NIPS 2017): Long Beach, California, USA, 4-9 December 2017, 10, 6447-6457
Learning individual-level causal effects from observational data, such as inferring the most effective medication for a specific patient, is a problem of growing importance for policy makers. The most important aspect of inferring causal effects from
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=narcis______::2428d2cc02a6af2e5d669a344c8a3177
https://dare.uva.nl/personal/pure/en/publications/causal-effect-inference-with-deep-latentvariable-models(fcc9c08f-4ed2-436d-a675-f4b74329928a).html
https://dare.uva.nl/personal/pure/en/publications/causal-effect-inference-with-deep-latentvariable-models(fcc9c08f-4ed2-436d-a675-f4b74329928a).html
Autor:
Louizos, C., Ullrich, K., Welling, M., von Luxburg, U., Guyon, I., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S.V.N., Garnett, R.
Publikováno v:
31st Conference on Advances in Neural Information Processing Systems (NIPS 2017): Long Beach, California, USA, 4-9 December 2017, 5, 3289-3299
Compression and computational efficiency in deep learning have become a problem of great significance. In this work, we argue that the most principled and effective way to attack this problem is by adopting a Bayesian point of view, where through spa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=narcis______::0979a5167682d0cc7d57705cb521da9f
https://dare.uva.nl/personal/pure/en/publications/bayesian-compression-for-deep-learning(d11626c6-d457-4254-a3a9-b6c0623d157a).html
https://dare.uva.nl/personal/pure/en/publications/bayesian-compression-for-deep-learning(d11626c6-d457-4254-a3a9-b6c0623d157a).html
Autor:
Louizos, C, Welling, M.
Publikováno v:
34th International Conference on Machine Learning, ICML 2017. 6 August 2017 through 11 August 2017, 5, 3480-3489
Proceedings of Machine Learning Research, 70, 2218-2227
Proceedings of the 34th International Conference on Machine Learning, Sydney, Australia, 2017.
Proceedings of Machine Learning Research, 70, 2218-2227
Proceedings of the 34th International Conference on Machine Learning, Sydney, Australia, 2017.
We reinterpret multiplicative noise in neural networks as auxiliary random variables that augment the approximate posterior in a variational setting for Bayesian neural networks. We show that through this interpretation it is both efficient and strai
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::12bdf9a347ec1241ec21648c039f9001
Argument extraction is the task of identifying arguments, along with their components in text. Arguments can be usually decomposed into a claim and one or more premises justifying it. Among the novel aspects of this work is the thematic domain itself
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______2127::b1644d3df3a03328ed0f1c3bb01a220b
https://pergamos.lib.uoa.gr/uoa/dl/object/uoadl:3071449
https://pergamos.lib.uoa.gr/uoa/dl/object/uoadl:3071449
Conference
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.