Hands-on reservoir computing: a tutorial for practical implementation
This manuscript serves a specific purpose: to give readers from fields such as material
science, chemistry, or electronics an overview of implementing a reservoir computing (RC) …
science, chemistry, or electronics an overview of implementing a reservoir computing (RC) …
A systematic literature review of the successors of “neuroevolution of augmenting topologies”
E Papavasileiou, J Cornelis… - Evolutionary …, 2021 - ieeexplore.ieee.org
NeuroEvolution (NE) refers to a family of methods for optimizing Artificial Neural Networks
(ANNs) using Evolutionary Computation (EC) algorithms. NeuroEvolution of Augmenting …
(ANNs) using Evolutionary Computation (EC) algorithms. NeuroEvolution of Augmenting …
Growing echo-state network with multiple subreservoirs
J Qiao, F Li, H Han, W Li - IEEE transactions on neural …, 2016 - ieeexplore.ieee.org
An echo-state network (ESN) is an effective alternative to gradient methods for training
recurrent neural network. However, it is difficult to determine the structure (mainly the …
recurrent neural network. However, it is difficult to determine the structure (mainly the …
Wind speed and wind direction forecasting using echo state network with nonlinear functions
Wind turbines are among the most popular sources of renewable energy. The energy
available from wind varies widely because wind energy is highly dependent on continually …
available from wind varies widely because wind energy is highly dependent on continually …
PSO-based growing echo state network
Y Li, F Li - Applied Soft Computing, 2019 - Elsevier
Reservoir computing (RC), with the idea of using a large randomly and sparsely connected
recurrent layer, has turned out to be an efficient paradigm for training recurrent neural …
recurrent layer, has turned out to be an efficient paradigm for training recurrent neural …
Evolution beats random chance: Performance-dependent network evolution for enhanced computational capacity
The quest to understand structure-function relationships in networks across scientific
disciplines has intensified. However, the optimal network architecture remains elusive …
disciplines has intensified. However, the optimal network architecture remains elusive …
Evolving memristive reservoir
X Shi, LL Minku, X Yao - IEEE Transactions on Neural …, 2023 - ieeexplore.ieee.org
In light of the dynamic plasticity, nanosize, and energy efficiency of memristors, memristive
reservoirs have attracted increasing attention in diverse fields of research recently. However …
reservoirs have attracted increasing attention in diverse fields of research recently. However …
Generating probabilistic predictions using mean-variance estimation and echo state network
In conventional time series prediction techniques, uncertainty associated with predictions
are usually ignored. Probabilistic predictors, on the other hand, can measure the uncertainty …
are usually ignored. Probabilistic predictors, on the other hand, can measure the uncertainty …
Evolving and training of neural network to play DAMA board game using NEAT algorithm
Neuroevolutionary algorithms, such as NeuroEvolution of Augmenting Topologies (NEAT) in
Machine Learning (ML) methods, are utilized for training and playing computer games due …
Machine Learning (ML) methods, are utilized for training and playing computer games due …
Latent representation in human–robot interaction with explicit consideration of periodic dynamics
This article presents a new data-driven framework for analyzing periodic physical human–
robot interaction (pHRI) in latent state space. The model representing pHRI is critical for …
robot interaction (pHRI) in latent state space. The model representing pHRI is critical for …