Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Izzo, Cosimo"'
A novel deep neural network framework -- that we refer to as Deep Dynamic Factor Model (D$^2$FM) --, is able to encode the information available, from hundreds of macroeconomic and financial time-series into a handful of unobserved latent states. Whi
Externí odkaz:
http://arxiv.org/abs/2007.11887
Publikováno v:
ESANN 2021 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Deep neural networks have gained momentum based on their accuracy, but their interpretability is often criticised. As a result, they are labelled as black boxes. In response, several methods have been proposed in the literature to explain their predi
Externí odkaz:
http://arxiv.org/abs/2006.04896
Autor:
Izzo, Cosimo
In this article we will analyse how to compute the contribution of each input value to its aggregate output in some nonlinear models. Regression and classification applications, together with related algorithms for deep neural networks are presented.
Externí odkaz:
http://arxiv.org/abs/1904.09615
This paper presents a tractable, transparent and broad-based domestic cyclical systemic risk indicator (d-SRI) that captures risks stemming from domestic credit, real estate markets, asset prices, and external imbalances. The d-SRI increases on avera
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______1687::2f306e3b4c4bf991869b425d120346f6
https://hdl.handle.net/10419/207604
https://hdl.handle.net/10419/207604