Zobrazeno 1 - 10
of 12
pro vyhledávání: '"Tullio Mancini"'
We propose an optimal architecture for deep neural networks of given size. The optimal architecture obtains from maximizing the lower bound of the maximum number of linear regions approximated by a deep neural network with a ReLu activation function.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::35f15fe990e757d15d53afa05c099788
https://eprints.soton.ac.uk/477462/
https://eprints.soton.ac.uk/477462/
Publikováno v:
Zaguán. Repositorio Digital de la Universidad de Zaragoza
instname
Journal of Risk and Financial Management; Volume 15; Issue 2; Pages: 71
instname
Journal of Risk and Financial Management; Volume 15; Issue 2; Pages: 71
Building on an economic model of rational Bitcoin mining, we measured the carbon footprint of Bitcoin mining power consumption using feed-forward neural networks. We found associated carbon footprints of 2.77, 16.08 and 14.99 MtCO2e for 2017, 2018 an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0a97e4dfea9b87f01b37987868f7b6f7
http://zaguan.unizar.es/record/118652
http://zaguan.unizar.es/record/118652
Environmental Engel curves describe how households' income relates to the pollution associated with the services and goods consumed. This paper estimates these curves with neural networks using the novel dataset constructed in Levinson and O'Brien. W
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::85c48a1015f93d5aa60b34a65e0d4e35
http://zaguan.unizar.es/record/119835
http://zaguan.unizar.es/record/119835
Publikováno v:
Neural networks : the official journal of the International Neural Network Society. 144
The aim of this paper is to propose a novel prediction model based on an ensemble of deep neural networks adapting the extremely randomized trees method originally developed for random forests. The extra-randomness introduced in the ensemble reduces
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::11500d3222d291e06d32b5fcef665af1
https://pubmed.ncbi.nlm.nih.gov/34487958
https://pubmed.ncbi.nlm.nih.gov/34487958
Publikováno v:
Applied spectroscopy. 75(7)
Raman spectroscopy has been used extensively to calculate CO
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=pmid________::3e9c48e47cb249dbc9b3b713e745bb36
https://pubmed.ncbi.nlm.nih.gov/33393350
https://pubmed.ncbi.nlm.nih.gov/33393350
Publikováno v:
Zaguán. Repositorio Digital de la Universidad de Zaragoza
instname
instname
This paper proposes a novel methodology to detect Granger causality on average in vector autoregressive settings using feedforward neural networks. The approach accommodates unknown dependence structures between elements of high-dimensional multivari
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7aec3ffa9e56041a4a6aa0e465898bb2
http://zaguan.unizar.es/record/108292
http://zaguan.unizar.es/record/108292
Publikováno v:
Journal of Risk and Financial Management, Vol 13, Iss 265, p 265 (2020)
This paper presents an overview of the procedures that are involved in prediction with machine learning models with special emphasis on deep learning. We study suitable objective functions for prediction in high-dimensional settings and discuss the r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b979eb5648c19a9d6d09d2f9e0c8908d
https://www.mdpi.com/1911-8074/13/11/265
https://www.mdpi.com/1911-8074/13/11/265
Publikováno v:
SSRN Electronic Journal.
We propose an optimal architecture for deep neural networks of given size. The optimal architecture obtains from maximizing the minimum number of linear regions approximated by a deep neural network with a ReLu activation function. The accuracy of th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5c97cc62320882f1da10faaa8104e516
https://doi.org/10.2139/ssrn.3578850
https://doi.org/10.2139/ssrn.3578850
Publikováno v:
SSRN Electronic Journal.
This paper proposes a novel methodology to detect Granger causality in mean in vector autoregressive settings using feedforward neural networks. The approach accommodates unknown dependence structures between the elements of highly-dimensional multiv
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1c262bf6c6ae94076728ab7889f4e0bb
https://doi.org/10.2139/ssrn.3543687
https://doi.org/10.2139/ssrn.3543687
Publikováno v:
Goldschmidt Abstracts.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a321135140e040a7b331793259ffbaa9
https://doi.org/10.46427/gold2020.2189
https://doi.org/10.46427/gold2020.2189