[HTML][HTML] Generalization properties of feed-forward neural networks trained on Lorenz systems
Neural networks are able to approximate chaotic dynamical systems when provided with
training data that cover all relevant regions of the system's phase space. However, many …
training data that cover all relevant regions of the system's phase space. However, many …
New results for prediction of chaotic systems using deep recurrent neural networks
Prediction of nonlinear and dynamic systems is a challenging task, however with the aid of
machine learning techniques, particularly neural networks, is now possible to accomplish …
machine learning techniques, particularly neural networks, is now possible to accomplish …
Neural network training using particle swarm optimization-A case study
M Kaminski - 2019 24th International Conference on Methods …, 2019 - ieeexplore.ieee.org
This paper presents analysis of multiparameter optimization realized applying Particle
Swarm Optimization (PSO). Model of Neural Network (NN) was selected as object. The main …
Swarm Optimization (PSO). Model of Neural Network (NN) was selected as object. The main …
Epileptic EEG classification via deep learning-based strange attractor
Y Lin, L Dong, Y Jiang, J Lian - Biomedical Signal Processing and Control, 2025 - Elsevier
Electroencephalography is commonly exploited in recording brains' electrical activities for
revealing the symptoms of various neurological diseases, eg, epileptic seizures. We …
revealing the symptoms of various neurological diseases, eg, epileptic seizures. We …
Fine-grained and multi-scale motif features for cross-subject mental workload assessment using Bi-lstm
Mental workload (MW) assessment is crucial for understanding human mental state. Cross-
subject MW analysis based on electroencephalogram (EEG) signals is an important way. In …
subject MW analysis based on electroencephalogram (EEG) signals is an important way. In …
Reconstruction of chaotic attractor for fractional-order tamaševičius system using recurrent neural networks
In this paper, a forecasting model using recur-rent neural networks (RNN) for reconstructing
the chaotic fractional-order Tamaševičius system states has been developed. The …
the chaotic fractional-order Tamaševičius system states has been developed. The …
Variation on the number of hidden nodes through multilayer perceptron networks to predict the cycle time
Multilayer Perceptron Network (MLP) has a better prediction Multilayer Perceptron Network
(MLP) has a better prediction performance compared to other networks since the structure …
(MLP) has a better prediction performance compared to other networks since the structure …
[PDF][PDF] New artificial neural network design for Chua chaotic system prediction using FPGA hardware co-simulation
WA Al-Musawi, WA Wali… - International Journal of …, 2022 - researchgate.net
This study aims to design a new architecture of the artificial neural networks (ANNs) using
the **linx system generator (XSG) and its hardware co-simulation equivalent model using …
the **linx system generator (XSG) and its hardware co-simulation equivalent model using …
Polar Representation of 2D Image Using Complex Exponential Spiking Neuron Network
L Zhang - Proceedings of the 52nd International Conference on …, 2023 - dl.acm.org
The paper introduces an innovative hybrid encoding method for images. It proposes a
conversion process where the image is transformed from the conventional Cartesian …
conversion process where the image is transformed from the conventional Cartesian …
Evaluating the effects of size and precision of training data on ANN training performance for the prediction of chaotic time series patterns
L Zhang - International Journal of Software Science and …, 2019 - igi-global.com
In this research, artificial neural networks (ANN) with various architectures are trained to
generate the chaotic time series patterns of the Lorenz attractor. The ANN training …
generate the chaotic time series patterns of the Lorenz attractor. The ANN training …