Identification of motion with echo state network

Ishu, K.; Zant, Tijn van der; Becanovic, Vlatko; Plöger, Paul G.

doi:10.1109/oceans.2004.1405751

Cited by 47 publications

(18 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Although, sparse matrices process the information faster than dense matrices, as a consequence a sparse reservoir can improve performance in time [1], [17]. Recently, an evolutionary algorithm was used to find the reservoir size, the spectral radius and the density of the reservoir matrix [9]. In addition, evolutionary and genetic algorithms were applied for optimizing the reservoir global parameters and for designing the connectivity of the reservoir [10]- [12].…”

Section: The Pso For Setting the Esn Modelmentioning

confidence: 99%

See 1 more Smart Citation

An experimental analysis of the Echo State Network initialization using the Particle Swarm Optimization

Basterrech

Alba

Snášel

2014

2014 Sixth World Congress on Nature and Biologically Inspired Computing (NaBIC 2014)

View full text Add to dashboard Cite

Abstract-This article introduces a robust hybrid method for solving supervised learning tasks, which uses the Echo State Network (ESN) model and the Particle Swarm Optimization (PSO) algorithm. An ESN is a Recurrent Neural Network with the hidden-hidden weights fixed in the learning process. The recurrent part of the network stores the input information in internal states of the network. Another structure forms a freememory method used as supervised learning tool. The setting procedure for initializing the recurrent structure of the ESN model can impact on the model performance. On the other hand, the PSO has been shown to be a successful technique for finding optimal points in complex spaces. Here, we present an approach to use the PSO for finding some initial hiddenhidden weights of the ESN model. We present empirical results that compare the canonical ESN model with this hybrid method on a wide range of benchmark problems.

show abstract

Section: The Pso For Setting the Esn Modelmentioning

confidence: 99%

“…A specific kind of RC methods uses topographic maps for initializing its weights [6]- [8]. Besides, an evolutionary algorithm was used for designing the reservoir [9]. Additionally, other metaheuristic techniques were applied for optimizing the reservoir global parameters, topology and reservoir weights was studied in [10]- [12].…”

Section: Introductionmentioning

confidence: 99%

An experimental analysis of the Echo State Network initialization using the Particle Swarm Optimization

Basterrech

Alba

Snášel

2014

2014 Sixth World Congress on Nature and Biologically Inspired Computing (NaBIC 2014)

View full text Add to dashboard Cite

show abstract

“…When it became evident that better results could be obtained by optimizing the reservoir to exhibit rich dynamics, rather than randomly generating it, many methods emerged to do just that (Ishu et al 2004;Xu et al 2005;Bush and Tsendjav 2005;Babinec and Pospichal 2005;Jiang et al 2008), mainly evolutionary, but with the network size prespecified or optimized separately from the topology and weights (Chatzidimitriou and Mitkas 2013).…”

Section: Evolutionary Neural Networkmentioning

confidence: 99%

Effective connectivity at synaptic level in humans: a review and future prospects

Gürcan

2014

Biol Cybern

View full text Add to dashboard Cite

Correct knowledge of the effective connectivity at the synaptic level in humans is a key prerequisite for increasing our understanding of the operation of the human central nervous system. Unfortunately, none of the current ambitious collaborative neuroscience projects pay enough attention to this topic and are thus unable to completely relate the microlevel properties of the system to its emergent macrolevel behaviors. In this review article, the problem of effective connectivity at the synaptic level in humans is explained, existing and possible computational approaches to fill explanatory gaps are reviewed, and the requisite characteristics of these approaches are considered.

show abstract

“…A number of optimization algorithms have already been proposed [25][26][27]. The main drawback of these methods for reservoir optimization is that they either use too many parameters, e.g.…”

Section: Parameter Optimizationmentioning

confidence: 99%

Optimization of echo state networks for drought prediction based on remote sensing data

Mohammadinezhad

Jalili

2013

2013 IEEE 8th Conference on Industrial Electronics and Applications (ICIEA)

View full text Add to dashboard Cite

In this paper, we used echo state networks -a class of recurrent neural networks -for prediction of drought based on remote sensing data. To this end, the drought index was obtained for a number of stations in different clime zones of Iran. For each station, we also extracted the corresponding vegetation indices based on satellite imagery. Our model takes the satellitebased features as input and outputs the severity of drought. One of the major challenges of echo state networks is optimization of the reservoir parameters. Here we used a method based on Kronecker product in order to substantially reduce the parameter space to be optimized. We then used various optimization techniques including genetic algorithms, simulated annealing and differential evolution. Our results show that the method based on differential evolution results in the best performance as compared to others.

show abstract

Identification of motion with echo state network

Cited by 47 publications

References 2 publications

An experimental analysis of the Echo State Network initialization using the Particle Swarm Optimization

An experimental analysis of the Echo State Network initialization using the Particle Swarm Optimization

Effective connectivity at synaptic level in humans: a review and future prospects

Optimization of echo state networks for drought prediction based on remote sensing data

Contact Info

Product

Resources

About