Juan-Pablo Ortega

Juan-Pablo Ortega

orcid

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 December 2018 in Neural Networks
Verified
Journal Article
Closed access
LGLyudmila Grigoryeva
Lyudmila Grigoryeva
JOJuan-Pablo Ortega
Juan-Pablo Ortega

18 March 2019 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
LGLukas Gonon
Lukas Gonon
JOJuan-Pablo Ortega
Juan-Pablo Ortega
The universal approximation properties with respect to L p -type criteria of three important families of reservoir computers with stochastic discrete-time semi-infinite inputs are shown. First, it is proven that linear reservoir systems with either polynomial or neural network readout maps are universal. More importantly, it is proven that the same property holds for two families with linear readouts, namely, trigonometric state-affine systems and echo state networks, which are the most widely used reservoir systems in applications. The linearity in the readouts is a key feature in supervised machine learning applications. It guarantees that these systems can be used in high-dimensional situations and in the presence of large data sets. The L p criteria used in this paper allow the formulation of universality results that do not necessarily impose almost sure uniform boundedness in the inputs or the fading memory property in the filter that needs to be approximated.

1 June 2021 in Neural Networks
Verified
Journal Article
Open access
LGLukas Gonon
Lukas Gonon
JOJuan-Pablo Ortega
Juan-Pablo Ortega
Echo state networks (ESNs) have been recently proved to be universal approximants for input/output systems with respect to various Lp-type criteria. When 1≤p<∞, only p-integrability hypotheses need to be imposed, while in the case p=∞ a uniform boundedness hypotheses on the inputs is required. This note shows that, in the last case, a universal family of ESNs can be constructed that contains exclusively elements that have the echo state and the fading memory properties. This conclusion could not be drawn with the results and methods available so far in the literature.

3 June 2021 in Physical Review E
Verified
Journal Article
Closed access
PDF file
LGLyudmila Grigoryeva
Lyudmila Grigoryeva
AHAllen Hart
Allen Hart
JOJuan-Pablo Ortega
Juan-Pablo Ortega
This paper shows that a large class of fading memory state-space systems driven by discrete-time observations of dynamical systems defined on compact manifolds always yields continuously differentiable synchronizations. This general result provides a powerful tool for the representation, reconstruction, and forecasting of chaotic attractors. It also improves previous statements in the literature for differentiable generalized synchronizations, whose existence was so far guaranteed for a restricted family of systems and was detected using Hölder exponent-based criteria.

26 May 2021 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Open access
CCChrista Cuchiero
Christa Cuchiero
LGLukas Gonon
Lukas Gonon
LGLyudmila Grigoryeva
Lyudmila Grigoryeva
JOJuan-Pablo Ortega
Juan-Pablo Ortega
JTJosef Teichmann
Josef Teichmann
A new explanation of the geometric nature of the reservoir computing (RC) phenomenon is presented. RC is understood in the literature as the possibility of approximating input-output systems with randomly chosen recurrent neural systems and a trained linear readout layer. Light is shed on this phenomenon by constructing what is called strongly universal reservoir systems as random projections of a family of state-space systems that generate Volterra series expansions. This procedure yields a state-affine reservoir system with randomly generated coefficients in a dimension that is logarithmically reduced with respect to the original system. This reservoir system is able to approximate any element in the fading memory filters class just by training a different linear readout for each different filter. Explicit expressions for the probability distributions needed in the generation of the projected reservoir system are stated, and bounds for the committed approximation error are provided.

1 October 2009 in American Journal of Mathematics
Verified
Journal Article
Closed access
PDF file
RFRui Loja Fernandes
Rui Loja Fernandes
JOJuan-Pablo Ortega
Juan-Pablo Ortega
TRTudor S. Ratiu
Tudor S. Ratiu
Every action on a Poisson manifold by Poisson diffeomorphisms lifts to a Hamiltonian action on its symplectic groupoid which has a canonically defined momentum map. We study various properties of this momentum map as well as its use in reduction.