Results 141 to 150 of about 233,583 (184)

BeamCraft: Deep Reinforcement Learning-DrivenMulti-Objective Beamforming for ISAC

Dao DN, Miao Y.
europepmc   +1 more source

Some of the next articles are maybe not open access.

Related searches:

Quaternion-Valued Echo State Networks

IEEE Transactions on Neural Networks and Learning Systems, 2015
Quaternion-valued echo state networks (QESNs) are introduced to cater for 3-D and 4-D processes, such as those observed in the context of renewable energy (3-D wind modeling) and human centered computing (3-D inertial body sensors). The introduction of QESNs is made possible by the recent emergence of quaternion nonlinear activation functions with ...
Yili, Xia, Cyrus, Jahanchahi, Danilo P, Mandic   +2 more
openaire   +4 more sources

Learning grammatical structure with Echo State Networks

Neural Networks, 2007
Echo State Networks (ESNs) have been shown to be effective for a number of tasks, including motor control, dynamic time series prediction, and memorizing musical sequences. However, their performance on natural language tasks has been largely unexplored until now.
Tong, Matthew H., Bickett, Adam D., Christiansen, Eric M., Cottrell, Garrison W.   +3 more
openaire   +4 more sources

fastESN: Fast Echo State Network

IEEE Transactions on Neural Networks and Learning Systems, 2023
Echo state networks (ESNs) are reservoir computing-based recurrent neural networks widely used in pattern analysis and machine intelligence applications. In order to achieve high accuracy with large model capacity, ESNs usually contain a large-sized internal layer (reservoir), making the evaluation process too slow for some applications.
Hai Wang, Xingyi Long, Xue-Xin Liu
openaire   +2 more sources

Convolutional Multitimescale Echo State Network

IEEE Transactions on Cybernetics, 2021
As efficient recurrent neural network (RNN) models, echo state networks (ESNs) have attracted widespread attention and been applied in many application domains in the last decade. Although they have achieved great success in modeling time series, a single ESN may have difficulty in capturing the multitimescale structures that naturally exist in ...
Qianli Ma, Enhuan Chen, Zhenxi Lin, Jiangyue Yan, Zhiwen Yu, Wing W. Y. Ng   +5 more
openaire   +2 more sources

Balanced echo state networks

Neural Networks, 2012
This paper investigates the interaction between the driving output feedback and the internal reservoir dynamics in echo state networks (ESNs). The interplay is studied experimentally on the multiple superimposed oscillators (MSOs) benchmark. The experimental data reveals a dual effect of the output feedback strength on the network dynamics: it drives ...
Danil, Koryakin, Johannes, Lohmann, Martin V, Butz   +2 more
openaire   +2 more sources

Regular echo state networks

Proceedings of the 36th Annual ACM Symposium on Applied Computing, 2021
Reservoir computing is a computational paradigm derived from recurrent neural network models. One of its most representative technique is the Echo State Network (ESN), which is usually composed by two salient components: reservoir and readout. The former is responsible by mapping temporal (or sequential) inputs into a high-dimensional space and the ...
Lucas Z. Bissaro, Yaochu Jin, Murillo G. Carneiro   +2 more
openaire   +1 more source

The copula echo state network

Pattern Recognition, 2012
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Chatzis, Sotirios P., Demiris, Yiannis
openaire   +3 more sources

Minimum Complexity Echo State Network

IEEE Transactions on Neural Networks, 2011
Reservoir computing (RC) refers to a new class of state-space models with a fixed state transition structure (the reservoir) and an adaptable readout form the state space. The reservoir is supposed to be sufficiently complex so as to capture a large number of features of the input stream that can be exploited by the reservoir-to-output readout mapping.
Ali, Rodan, Peter, Tino
openaire   +2 more sources