Zobrazeno 1 - 10
of 61
pro vyhledávání: '"Bottou, L��on"'
Autor:
Yadav, Chhavi, Bottou, L��on
Although the popular MNIST dataset [LeCun et al., 1994] is derived from the NIST database [Grother and Hanaoka, 1995], the precise processing steps for this derivation have been lost to time. We propose a reconstruction that is accurate enough to ser
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a5c24c5e1e00ac0c2bdb1cef28aab0ee
Autor:
Defazio, Aaron, Bottou, L��on
The application of stochastic variance reduction to optimization has shown remarkable recent theoretical and practical success. The applicability of these techniques to the hard non-convex optimization problems encountered during training of modern d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cac010fd70a81a03965862c641eea5a9
Autor:
Defazio, Aaron, Bottou, L��on
We introduce a new normalization technique that exhibits the fast convergence properties of batch normalization using a transformation of layer weights instead of layer outputs. The proposed technique keeps the contribution of positive and negative w
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7114b1064a8fb4c586bea29e6fc7725f
Autor:
Arjovsky, Martin, Bottou, L��on
The goal of this paper is not to introduce a single algorithm or method, but to make theoretical steps towards fully understanding the training dynamics of generative adversarial networks. In order to substantiate our theoretical analysis, we perform
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d849dddf32a3e1410b4524eb7376579c
We introduce a new algorithm named WGAN, an alternative to traditional GAN training. In this new model, we show that we can improve the stability of learning, get rid of problems like mode collapse, and provide meaningful learning curves useful for d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bd490c07c281a3f2f6de5566f572bf64
Distillation (Hinton et al., 2015) and privileged information (Vapnik & Izmailov, 2015) are two techniques that enable machines to learn from other machines. This paper unifies these two techniques into generalized distillation, a framework to learn
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6251804a1fd99abb756e77012ab8e1f6
http://arxiv.org/abs/1511.03643
http://arxiv.org/abs/1511.03643
Algorithms for hyperparameter optimization abound, all of which work well under different and often unverifiable assumptions. Motivated by the general challenge of sequentially choosing which algorithm to use, we study the more specific task of choos
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1489d29417edfee42594f18cb3e0154e
http://arxiv.org/abs/1508.02933
http://arxiv.org/abs/1508.02933
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=narcis______::b2e78f59111340e71ff9be7b2e8e1f95
https://dare.uva.nl/personal/pure/en/publications/27th-annual-conference-on-neural-information-processing-systems-2013-december-510-lake-tahoe-nevada-usa(cfadc2b9-70e9-4f4f-ac59-dc070d778c46).html
https://dare.uva.nl/personal/pure/en/publications/27th-annual-conference-on-neural-information-processing-systems-2013-december-510-lake-tahoe-nevada-usa(cfadc2b9-70e9-4f4f-ac59-dc070d778c46).html
Autor:
Boyles, L., Welling, M., Bartlett, P., Pereira, F.C.N., Burges, C.J.C., Bottou, L., Weinberger, K.Q.
Publikováno v:
26th Annual Conference on Neural Information Processing Systems 2012: December 3-6, 2012, Lake Tahoe, Nevada, USA, 4, 2969-2977
We introduce a new prior for use in Nonparametric Bayesian Hierarchical Clustering. The prior is constructed by marginalizing out the time information ofKingman’s coalescent, providing a prior over tree structures which we call the Time-Marginalize
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=narcis______::ad4b903bd43ac5dd767d45f62fc0ff11
https://dare.uva.nl/personal/pure/en/publications/the-timemarginalized-coalescent-prior-for-hierarchical-clustering(6d59912e-0401-413f-a596-2470ed74c69b).html
https://dare.uva.nl/personal/pure/en/publications/the-timemarginalized-coalescent-prior-for-hierarchical-clustering(6d59912e-0401-413f-a596-2470ed74c69b).html
Autor:
Bottou, L��on, Peters, Jonas, Qui��onero-Candela, Joaquin, Charles, Denis X., Chickering, D. Max, Portugaly, Elon, Ray, Dipankar, Simard, Patrice, Snelson, Ed
This work shows how to leverage causal inference to understand the behavior of complex learning systems interacting with their environment and predict the consequences of changes to the system. Such predictions allow both humans and algorithms to sel
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6224f32e011a3819f9add98e46df2d4e
http://arxiv.org/abs/1209.2355
http://arxiv.org/abs/1209.2355