English
Related papers

Related papers: Echo state networks are universal

200 papers

We derive new upper and lower bounds on the fading number of multiple-input single-output (MISO) fading channels of general (not necessarily Gaussian) regular law with spatial and temporal memory. The fading number is the second term, after…

Information Theory · Computer Science 2007-07-16 Stefan M. Moser

The paper investigates a new type of truly critical echo state networks where individual transfer functions for every neuron can be modified to anticipate the expected next input. Deviations from expected input are only forgotten slowly in…

Neural and Evolutionary Computing · Computer Science 2017-03-07 Norbert Michael Mayer

In this article, we explore the effects of memory terms in continuous-layer Deep Residual Networks by studying Neural ODEs (NODEs). We investigate two types of models. On one side, we consider the case of Residual Neural Networks with…

Optimization and Control · Mathematics 2021-10-19 Domènec Ruiz-Balet , Elisa Affili , Enrique Zuazua

Lossless Feedback Delay Networks (FDNs) are commonly used as a design prototype for artificial reverberation algorithms. The lossless property is dependent on the feedback matrix, which connects the output of a set of delays to their…

Systems and Control · Computer Science 2017-04-05 Sebastian J. Schlecht , Emanuel A. P. Habets

Neural networks (NNs) are known for their high predictive accuracy in complex learning problems. Beside practical advantages, NNs also indicate favourable theoretical properties such as universal approximation (UA) theorems. Binarized…

Machine Learning · Computer Science 2021-02-05 Mikail Yayla , Mario Günzel , Burim Ramosaj , Jian-Jia Chen

Recurrent neural networks (RNNs) and transformers have been shown to be Turing-complete, but this result assumes infinite precision in their hidden representations, positional encodings for transformers, and unbounded computation time in…

Computational Complexity · Computer Science 2023-09-27 Ankur Mali , Alexander Ororbia , Daniel Kifer , Lee Giles

Systems that evolve towards a state from which they cannot depart are common in nature. But the fluctuation-dissipation theorem, a fundamental result in statistical mechanics, is mainly restricted to systems near-stationarity. In processes…

Statistical Mechanics · Physics 2023-10-25 Prajwal Padmanabha , Sandro Azaele , Amos Maritan

A probabilistic framework to study the dependence structure induced by deterministic discrete-time state-space systems between input and output processes is introduced. General sufficient conditions are formulated under which output…

Machine Learning · Statistics 2025-03-13 Juan-Pablo Ortega , Florian Rossmannek

In this paper we introduce a new framework to train an Echo State Network to predict real valued time-series. The method consists in projecting the output of the internal layer of the network on a space with lower dimensionality, before…

Neural and Evolutionary Computing · Computer Science 2017-01-10 Sigurd Løkse , Filippo Maria Bianchi , Robert Jenssen

The universal approximation theorem asserts that a single hidden layer neural network approximates continuous functions with any desired precision on compact sets. As an existential result, the universal approximation theorem supports the…

Machine Learning · Computer Science 2023-09-15 Wington L. Vital , Guilherme Vieira , Marcos Eduardo Valle

Fixed point iterations are known to generate chaos, for some values in their parameter range. It is an established fact that Turing Machines are fixed point iterations. However, as these Machines operate in integer space, the standard…

Computational Complexity · Computer Science 2015-07-06 Nabarun Mondal , Partha P. Ghosh

The robust distributed state estimation for a class of continuous-time linear time-invariant systems is achieved by a novel kernel-based distributed observer, which, for the first time, ensures fixed-time convergence properties. The…

Systems and Control · Electrical Eng. & Systems 2022-09-21 Pudong Ge , Peng Li , Boli Chen , Fei Teng

Inspired by the numerical solution of ordinary differential equations, in this paper we propose a novel Reservoir Computing (RC) model, called the Euler State Network (EuSN). The presented approach makes use of forward Euler discretization…

Machine Learning · Computer Science 2023-03-27 Claudio Gallicchio

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…

Dynamical Systems · Mathematics 2021-06-09 Lyudmila Grigoryeva , Allen Hart , Juan-Pablo Ortega

A new mathematical model of neural networks described by diffusive FitzHugh-Nagumo equations with memristors and linear synaptic coupling is proposed and investigated. The existence of absorbing set for the solution semiflow in the energy…

Analysis of PDEs · Mathematics 2023-08-09 Yuncheng You , Jing Tian , Junyi Tu

In this paper we study time semi-discrete approximations of a class of exponentially stable infinite dimensional systems with unbounded feedbacks. It has recently been proved that for time semi-discrete systems, due to high frequency…

Optimization and Control · Mathematics 2013-06-18 Zayd Hajjej , Mohamed Balegh

We derive fundamental lower bounds on the connectivity and the memory requirements of deep neural networks guaranteeing uniform approximation rates for arbitrary function classes in $L^2(\mathbb R^d)$. In other words, we establish a…

Machine Learning · Computer Science 2018-05-17 Helmut Bölcskei , Philipp Grohs , Gitta Kutyniok , Philipp Petersen

Normalizing flows have grown more popular over the last few years; however, they continue to be computationally expensive, making them difficult to be accepted into the broader machine learning community. In this paper, we introduce a…

Machine Learning · Computer Science 2021-12-15 Achintya Gopal

Spatio-temporal data and processes are prevalent across a wide variety of scientific disciplines. These processes are often characterized by nonlinear time dynamics that include interactions across multiple scales of spatial and temporal…

Machine Learning · Statistics 2017-08-18 Patrick L. McDermott , Christopher K. Wikle

It is a widely accepted fact that data representations intervene noticeably in machine learning tools. The more they are well defined the better the performance results are. Feature extraction-based methods such as autoencoders are…

Neural and Evolutionary Computing · Computer Science 2018-06-12 Naima Chouikhi , Boudour Ammar , Adel M. Alimi