User profiles for Gabriel Borrageiro
Gabriel BorrageiroHonorary Research Fellow, University College London Verified email at ucl.ac.uk Cited by 24 |
The recurrent reinforcement learning crypto agent
We demonstrate a novel application of online transfer learning for a digital assets trading
agent. This agent uses a powerful feature space representation in the form of an echo state …
agent. This agent uses a powerful feature space representation in the form of an echo state …
Reinforcement learning for systematic FX trading
We explore online inductive transfer learning, with a feature representation transfer from a
radial basis function network formed of Gaussian mixture model hidden processing units to a …
radial basis function network formed of Gaussian mixture model hidden processing units to a …
Online learning with radial basis function networks
Financial time series are characterised by their nonstationarity and autocorrelation. Even if
these time series are differenced, technically ensuring their stationarity, they experience …
these time series are differenced, technically ensuring their stationarity, they experience …
Sequential asset ranking in nonstationary time series
We extend the research into cross-sectional momentum trading strategies. Our main result
is our novel ranking algorithm, the naive Bayes asset ranker (nbar), which we use to select …
is our novel ranking algorithm, the naive Bayes asset ranker (nbar), which we use to select …
[BOOK][B] Online learning in financial time series
G Borrageiro - 2022 - search.proquest.com
… Gabriel Borrageiro … I, Gabriel Borrageiro, confirm that the work presented in this thesis is
my own. Where information has been derived from other sources, I confirm that this has been …
my own. Where information has been derived from other sources, I confirm that this has been …
[PDF][PDF] Sequential Asset Ranking within Nonstationary Time Series.
Financial time series are both autocorrelated and nonstationary, presenting modelling
challenges that violate the independent and identically distributed random variables assumption …
challenges that violate the independent and identically distributed random variables assumption …
Formulation of natural cyclodecapeptides for surface sterilisation.
CM Borrageiro - 2023 - scholar.sun.ac.za
… By submitting this thesis electronically, I Christopher Borrageiro declare that the entirety of
the work contained therein is my own, original work, that I am the sole author thereof (save to …
the work contained therein is my own, original work, that I am the sole author thereof (save to …
Anthroponymy of marriers from parishes of Madeira (16th to 20th century), Portuguese to English translation of four photographic catalogues on the history of clothing …
CBR Chaves - 2024 - digituma.uma.pt
The present report aims to detail the activities undertaken during the curricular traineeship
in Translation and research project developed at the Centre for Atlantic History Studies — …
in Translation and research project developed at the Centre for Atlantic History Studies — …
Latent variable-based reinforcement learning for fx trading
A Mundo - 2021 - politesi.polimi.it
The Foreign Exchange, also known as Forex, is a highly dynamic and active market for
trading currencies, offering participants an exciting and challenging possibility to develop …
trading currencies, offering participants an exciting and challenging possibility to develop …
From'-Omics' to Biomarkers and Mechanisms in Parkinson's Disease: Growth Hormone Receptor and GPNMB
MED Ortiz - 2022 - search.proquest.com
Parkinson’s disease (PD) is a devastating neurodegenerative disorder that affects an
estimated~ 5 million people worldwide and is associated with intracellular α-synuclein protein …
estimated~ 5 million people worldwide and is associated with intracellular α-synuclein protein …