Results 151 to 160 of about 233,583 (184)
Some of the next articles are maybe not open access.
2020
Noisy or adverse input is a threat to the safe deployment of neural networks in production. To ensure the safe operations of such networks they need to be hardened to work under such conditions. Abstract interpretation, as a tool to formally verify properties of computations, can be used for this task.
Christoph Walter Senn, Itsuo Kumazawa
openaire +1 more source
Noisy or adverse input is a threat to the safe deployment of neural networks in production. To ensure the safe operations of such networks they need to be hardened to work under such conditions. Abstract interpretation, as a tool to formally verify properties of computations, can be used for this task.
Christoph Walter Senn, Itsuo Kumazawa
openaire +1 more source
The 2010 International Joint Conference on Neural Networks (IJCNN), 2010
In this paper we introduce the Graph Echo State Network (GraphESN) model, a generalization of the Echo State Network (ESN) approach to graph domains. GraphESNs allow for an efficient approach to Recursive Neural Networks (RecNNs) modeling extended to deal with cyclic/acyclic, directed/undirected, labeled graphs.
GALLICCHIO, CLAUDIO, MICHELI, ALESSIO
openaire +2 more sources
In this paper we introduce the Graph Echo State Network (GraphESN) model, a generalization of the Echo State Network (ESN) approach to graph domains. GraphESNs allow for an efficient approach to Recursive Neural Networks (RecNNs) modeling extended to deal with cyclic/acyclic, directed/undirected, labeled graphs.
GALLICCHIO, CLAUDIO, MICHELI, ALESSIO
openaire +2 more sources
Input Routed Echo State Networks
ESANN 2022 proceedings, 2022We introduce a novel Reservoir Computing (RC) approach for multi-dimensional temporal signals. Our proposal is based on routing the different dimensions of the driving input towards different dynamical sub-modules in a multi-reservoir architecture.
Argentieri, Luca +2 more
openaire +2 more sources
Analysis and Design of Echo State Networks
Neural Computation, 2007The design of echo state network (ESN) parameters relies on the selection of the maximum eigenvalue of the linearized system around zero (spectral radius). However, this procedure does not quantify in a systematic manner the performance of the ESN in terms of approximation error.
Ozturk, Mustafa C. +2 more
openaire +3 more sources
Echo State wireless sensor networks
2008 IEEE Workshop on Machine Learning for Signal Processing, 2008This paper addresses the question of temporal learning in spatially distributed wireless sensor networks (WSN). We propose to fuse WSNs with the echo states network learning concepts to infer the spatio-temporal dynamics of the data collaboratively measured by sensors.
Dmitriy Shutin, Gernot Kubin
openaire +1 more source
Predicting aging transition using Echo state network
Chaos: An Interdisciplinary Journal of Nonlinear Science, 2023It is generally known that in a mixture of coupled active and inactive nonlinear oscillators, the entire system may stop oscillating and become inactive if the fraction of active oscillators is reduced to a critical value. This emerging phenomenon, called the “aging transition,” can be analytically predicted from the view point of cluster ...
Biswambhar Rakshit +3 more
openaire +2 more sources
Restricted Echo State Networks
2016Echo state networks are a powerful type of reservoir neural network, but the reservoir is essentially unrestricted in its original formulation. Motivated by limitations in neuromorphic hardware, we remove combinations of the four sources of memory—leaking, loops, cycles, and discrete time—to determine how these influence the suitability of the ...
Aaron Stockdill, Kourosh Neshatian
openaire +1 more source
Attention Based Echo State Network
Proceedings of the 2019 11th International Conference on Machine Learning and Computing, 2019Recurrent neural networks (RNNs) are widely studied in recent years, since RNNs are capable of modeling the significant nonlinear dynamical systems. Echo state network (ESN) is a novel type of RNN with an interconnected reservoir to model temporal dynamics of complex sequential information. In this paper, a novel ESN structure is developed and employed
Chongdang Liu +3 more
openaire +1 more source
2006
We are interested in the optimization of the recurrent connection structure of Echo State Networks (ESNs), because their topology can strongly influence performance. We study ESN predictive capacity by numerical simulations on Mackey-Glass time series, and find that a particular small subset of ESNs is much better than ordinary ESNs provided that the ...
Márton Albert Hajnal, András Lőrincz
openaire +1 more source
We are interested in the optimization of the recurrent connection structure of Echo State Networks (ESNs), because their topology can strongly influence performance. We study ESN predictive capacity by numerical simulations on Mackey-Glass time series, and find that a particular small subset of ESNs is much better than ordinary ESNs provided that the ...
Márton Albert Hajnal, András Lőrincz
openaire +1 more source
Hierarchical Dynamics in Deep Echo State Networks
2022Reservoir computing (RC) is a popular approach to the efficient design of recurrent neural networks (RNNs), where the dynamical part of the model is initialized and left untrained. Deep echo state networks (ESNs) combined the deep learning approach with RC, by structuring the reservoir in multiple layers, thus offering the striking advantage of ...
Tortorella D., Gallicchio C., Micheli A.
openaire +1 more source