Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 52 for “"Echo State Network"”.
-
Architectural designs of Echo State Network
… systematically the reservoir construction of Echo State Network (ESN). This thesis proposes two very simple deterministic ESN organisation (Simple Cycle reservoir (SCR) and Cycle Reservoir with Jumps (CRJ). Simple Cycle reservoir (SCR) is sufficient to obtain performances comparable to those …
-
Design of a Neuromemristive Echo State Network Architecture
Echo state neural networks (ESNs) provide an efficient classification technique for spatiotemporal signals. The feedback connections in the ESN enable feature extraction in both spatial and temporal components in time series data. This property has been used in several application domains such as …
-
Two-Phase Buck Converter Optimize by Echo State Network
… efficiency. The inspiration of the neural network is derived from the biological brain, neural is similar with the human neural, and the synaptic weights can treat as the connection between two nodes. Reservoir computing can be seen as an extension of the neural network since it is a …
-
Exploring the Use of an Echo State Network in Modeling Turbulent Jet Behavior
This work investigates the use of an Echo State Network (ESN) to predict turbulent jet flow behavior. ESNs are a particular class of Recurrent Neural Networks (RNNs) that have been shown to model transient chaotic systems while avoiding some of the difficulties associated with training other types …
-
Data-Driven Predictions of Dynamical Systems using Echo State Network with Transfer Learning
This dissertation extensively explores fluid dynamics and chaos theory, primarily focusing on investigating the Shallow Water Equations (SWE) and the Kuramoto-Sivashinsky (KS) equation. These two paradigms are interconnected yet distinct realms within the study of complex systems. The SWE is a …
-
Reservoir Computing pro průmyslové aplikace
… cílem práce je ověřit účinnost a přesnost metody echo state network v predikci časových řad. K dosažení tohoto cíle je použit dataset z výrobního stroje a je implementován algoritmus echo state network. Jsou analyzovány výsledky a jsou rovněž porovnány s výsledky předchozích studií v oblasti …
-
Lane Change Prediction in the Urban Area
… changes in the urban area is applied with an Echo State Network. First, existing methods with a special focus on input variables and results were evaluated to derive input variables with regard to lane change and no lane change sequences. The data for this first analyses were obtained from a …
-
Análise Comparativa de Redes Neurais Artificiais para Previsão Diária de Demanda Elétrica no Sistema Interligado Nacional
… Unidimensional, Long Short-Term Memory e Echo State Network na previsão multihorária das 24 horas do dia seguinte para os subsistemas elétricos do Sistema Interligado Nacional. Os resultados demonstraram que, com exceção da Echo state network, cada arquitetura apresentou desempenho …
-
Accelerating Stochastic Random Projection Neural Networks
Artificial Neural Network (ANN), a computational model based on the biological neural networks, has a recent resurgence in machine intelligence with breakthrough results in pattern recognition, speech recognition, and mapping. This has led to a growing interest in designing dedicated hardware …
-
Stochastic modeling using machine learning and stochastic differential equations
… demonstrated promising results of using neural networks to parameterize SDEs (referred to as a neural SDE framework). Further studies have demonstrated how machine learning, specifically Recurrent Neural Networks (RNNS), can be used for predicting the future values of time-dependent data. The …
-
Modeling spatio-temporal data using a Bayesian probabilistic cellular automata framework
… probabilities that describe the evolution of the state of the cells across space and time. One implementation of a stochastic cellular automata for such data is with a spatio-temporal generalized linear model (or mixed model), with the local rule covariates being included in the transformed mean …
-
Short-range machine learning forecasts - North Atlantic basin activity
… of accumulated cyclone energy for 2025 using an Echo State Network (ESN). Initially, complex wavelets are employed to detangle persistent signals within the datasets, enhancing our understanding of experimental bounds and signal behavior. Subsequently, recognizing the intrinsic periodicity of …
-
Alternative learning strategies for spatio-temporal processes of complex animal behavior
… expansions produced by a spatio-temporal echo state network are used as features in a hierarchical generalized linear model for predicting spatial patterns of mallard duck settling pattern counts. Lastly, Bayesian inverse reinforcement learning is developed to estimate the behavioral state …
-
Robust Reservoir Computing Approaches for Predicting Cardiac Electrical Dynamics
… in this context are time series of observed state variables, without prior knowledge of the system dynamics. The reservoir computing framework, a learning paradigm derived from recurrent neural network concepts and most commonly realized as an echo state network (ESN), offers a streamlined …
-
Polynomial Functors in Agda: Theory and Practice
… Lorenz system, the Hodkgin-Huxley model, and an Echo-State Network that learns the Lorenz dynamics. Commuting squares are used as a way of showing that one dynamical system can be made to simulate another.
-
MIMO-OFDM Symbol Detection via Echo State Networks
Echo state network (ESN) is a specific neural network structure composed of high dimensional nonlinear dynamics and learned readout weights. This thesis considers applying ESN for symbol detection in multiple-input, multiple-output orthogonal frequency-division multiplexing (MIMO-OFDM) systems. A …
-
A Cost-Efficient Digital ESN Architecture on FPGA
Echo State Network (ESN) is a recently developed machine-learning paradigm whose processing capabilities rely on the dynamical behavior of recurrent neural networks (RNNs). Its performance metrics outperform traditional RNNs in nonlinear system identification and temporal information processing. In …
-
An echo state model of non-Markovian reinforcement learning
… operate in real-world domains. Theoretically the state-action space must exhibit the Markov property in order for reinforcement learning to be applicable. Empirical evidence, however, suggests that reinforcement learning also applies to domains where the state-action space is approximately …
Page 1 of 3