Results 61 to 70 of about 233,583 (184)
Regularized Taylor Echo State Networks for Predictive Control of Partially Observed Systems
IEEE Access, 2016 The existing neural networks suffer from partial observation while modeling and controlling dynamic systems. In this paper, a new linearized recurrent neural network, the Taylor expanded echo state network (TESN), is proposed for predictive control of ...
Kui Xiang +5 more
doaj +1 more source
Multiband multi-echo imaging of simultaneous oxygenation and flow timeseries for resting state connectivity. [PDF]
PLoS ONE, 2017 A novel sequence has been introduced that combines multiband imaging with a multi-echo acquisition for simultaneous high spatial resolution pseudo-continuous arterial spin labeling (ASL) and blood-oxygenation-level dependent (BOLD) echo-planar imaging ...
Alexander D Cohen +3 more
doaj +1 more source
Echo State Networks: analysis, training and predictive control
, 2019 The goal of this paper is to investigate the theoretical properties, the training algorithm, and the predictive control applications of Echo State Networks (ESNs), a particular kind of Recurrent Neural Networks. First, a condition guaranteeing incremetal
albertini +12 more
core +1 more source
Recurrent kernel machines : computing with infinite echo state networks [PDF]
, 2012 Echo state networks (ESNs) are large, random recurrent neural networks with a single trained linear readout layer. Despite the untrained nature of the recurrent weights, they are capable of performing universal computations on temporal input data, which ...
Hermans, Michiel, Schrauwen, Benjamin
core +2 more sources
Analysis of Imperfect Rephasing in Photon Echo-Based Quantum Memories
Entropy, 2022 Over the last two decades, quantum memories have been intensively studied for potential applications of quantum repeaters in quantum networks. Various protocols have also been developed. To satisfy no noise echoes caused by spontaneous emission processes,
Byoung S. Ham
doaj +1 more source
Relative entropy minimizing noisy non-linear neural network to approximate stochastic processes
, 2014 A method is provided for designing and training noise-driven recurrent neural networks as models of stochastic processes. The method unifies and generalizes two known separate modeling approaches, Echo State Networks (ESN) and Linear Inverse Modeling ...
Galtier, Mathieu N. +3 more
core +2 more sources
Optimizing Echo State Networks for Static Pattern Recognition [PDF]
, 2017 Static pattern recognition requires a machine to classify an object on the basis of a combination of attributes and is typically performed using machine learning techniques such as support vector machines and multilayer perceptrons.
Day, CR +3 more
core +2 more sources
Adaptive state-feedback echo state networks for temporal sequence learning
Scientific ReportsEcho State Networks are recurrent neural networks that leverage a random reservoir’s dynamics, training only a simple readout layer. This approach is computationally efficient but limits network performance.
Codrin A. Lupascu, Daniel Coca
doaj +1 more source
Mean-field theory of echo state networks [PDF]
Physical Review E, 2013 Dynamical systems driven by strong external signals are ubiquitous in nature and engineering. Here we study "echo state networks," networks of a large number of randomly connected nodes, which represent a simple model of a neural network, and have important applications in machine learning. We develop a mean-field theory of echo state networks.
Massar, Serge, Massar, M
openaire +2 more sources
Edge of Stability Echo State Network
IEEE Transactions on Neural Networks and Learning SystemsEcho State Networks (ESNs) are time-series processing models working under the Echo State Property (ESP) principle. The ESP is a notion of stability that imposes an asymptotic fading of the memory of the input. On the other hand, the resulting inherent architectural bias of ESNs may lead to an excessive loss of information, which in turn harms the ...
Andrea Ceni, Claudio Gallicchio
openaire +4 more sources