Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Paul Mineiro"'
Autor:
Wangda Zhang, Matteo Interlandi, Paul Mineiro, Shi Qiao, Nasim Ghazanfari, Karlen Lie, Marc Friedman, Rafah Hosn, Hiren Patel, Alekh Jindal
Modern analytical workloads are highly heterogeneous and massively complex, making generic query optimizers untenable for many customers and scenarios. As a result, it is important to specialize these optimizers to instances of the workloads. In this
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e72e46784ce4aeb6000cd62926cc3d45
http://arxiv.org/abs/2210.13625
http://arxiv.org/abs/2210.13625
In this paper, we provide a summary of the mathematical and computational techniques that have enabled learning reductions to effectively address a wide class of tasks, and show that this approach to solving machine learning problems can be broadly u
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::69a854ffee3fbd6b76cbcc198f2fbb84
Autor:
Paul Mineiro, Nikos Karampatziakis
Publikováno v:
Machine Learning and Knowledge Discovery in Databases ISBN: 9783319235271
ECML/PKDD (1)
ECML/PKDD (1)
Many modern multiclass and multilabel problems are characterized by increasingly large output spaces. For these problems, label embeddings have been shown to be a useful primitive that can improve computational and statistical efficiency. In this wor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::85727a79e38439d4460930e88a6a1071
https://doi.org/10.1007/978-3-319-23528-8_3
https://doi.org/10.1007/978-3-319-23528-8_3
Autor:
Paul Mineiro, Javier R. Movellan
Publikováno v:
Machine Learning. 32:85-100
This paper analyzes the issue of catastrophic fusion, a problem that occurs in multimodal recognition systems that integrate the output from several modules while working in non-stationary environments. For concreteness we frame the analysis with reg
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1f8b30cb20ba62ce0bfe6f89eccfca91
https://doi.org/10.1023/a:1007468413059
https://doi.org/10.1023/a:1007468413059
Publikováno v:
SIGMOD Conference
Statistical Machine Learning has undergone a phase transition from a pure academic endeavor to being one of the main drivers of modern commerce and science. Even more so, recent results such as those on tera-scale learning [1] and on very large neura
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3fd9130ba8edadb2fe552ed1a0a8f8a8
https://doi.org/10.1145/2463676.2465338
https://doi.org/10.1145/2463676.2465338
Publikováno v:
ICDE
Statistical Machine Learning has undergone a phase transition from a pure academic endeavor to being one of the main drivers of modern commerce and science. Even more so, recent results such as those on tera-scale learning [1] and on very large neura
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b5d0030769a8333d3eb97f83333a9c7a
https://doi.org/10.1109/icde.2013.6544913
https://doi.org/10.1109/icde.2013.6544913
Publikováno v:
Neural computation. 14(7)
We present a Monte Carlo approach for training partially observable diffusion processes. We apply the approach to diffusion networks, a stochastic version of continuous recurrent neural networks. The approach is aimed at learning probability distribu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4542e618d21e3c406d170c245c710eab
https://pubmed.ncbi.nlm.nih.gov/12079544
https://pubmed.ncbi.nlm.nih.gov/12079544
Autor:
David Zipser, Paul Mineiro
Publikováno v:
Neural computation. 10(2)
The relative contributions of feedforward and recurrent connectivity to the direction-selective responses of cells in layer IVB of primary visual cortex are currently the subject of debate in the neuroscience community. Recently, biophysically detail
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::35e3f1052cd940002c50d91f55cac038
https://pubmed.ncbi.nlm.nih.gov/9472486
https://pubmed.ncbi.nlm.nih.gov/9472486