Differential evolution (DE) is a simple and efficient population-based stochastic algorithm for solving global numerical optimization problems. DE largely depends on parameter values search strategy. Knowledge how to tune the best of these parameters scarce. This paper aims present consistent methodology tuning optimal parameters. At heart use an artificial neural network (ANN) that learns draw...

Many statistical modeling procedures involve one or more tuning parameters tocontrol the model complexity. These can be bandwidth in thekernel smoothing method nonparametric regression and density estimation orbe regularization parameter for feature selectionin high dimensional modeling. Tuning selection plays critical rolesin machine learning. For massive data analysis,commonly-used methods su...

This paper presents a comparison between the use of particle swarm optimization and the use of genetic algorithms for tuning the parameters of a novel fuzzy classifier. In the previous work on the classifier, the large amount of time needed by genetic algorithms has been significantly diminished by using an optimized initial population. Even with this improvement, the time spent on tuning the p...

Meta-heuristic algorithms should be compared using the best parameter values for all the involved algorithms. However, this is often unrealised despite the existence of several parameter tuning approaches. In order to further popularise tuning, this paper introduces a new tuning method CRS-Tuning that is based on meta-evolution and our novel method for comparing and ranking evolutionary algorit...

A central theme of systems neuroscience is to characterize the tuning of neural responses to sensory 12 stimuli or the production of movement. Statistically, we often want to estimate the parameters of the 13 tuning curve, such as preferred direction, as well as the associated degree of uncertainty, characterized 14 by errorbars. Here we present a new sampling-based, Bayesian method that allows...

A central theme of systems neuroscience is to characterize the tuning of neural responses to sensory stimuli or the production of movement. Statistically, we often want to estimate the parameters of the tuning curve, such as preferred direction, as well as the associated degree of uncertainty, characterized by error bars. Here we present a new sampling-based, Bayesian method that allows the est...

Cronin B, Stevenson IH, Sur M, Körding KP. Hierarchical Bayesian modeling and Markov chain Monte Carlo sampling for tuningcurve analysis. J Neurophysiol 103: 591–602, 2010. First published November 4, 2009; doi:10.1152/jn.00379.2009. A central theme of systems neuroscience is to characterize the tuning of neural responses to sensory stimuli or the production of movement. Statistically, we often...

One of the issues in tuning an output probability of a Bayesian network by changing multiple parameters is the relative amount of the individual parameter changes. In an existing heuristic parameters are tied such that their changes induce locally a maximal change of the tuned probability. This heuristic, however, may reduce the attainable values of the tuned probability considerably. In anothe...

Control of systems with time delay is difficult as compared to simple process control. Numerous parameters estimation techniques for the control implementation of non-linear systems with time delays are available in literature, but these techniques become cumbersome while tuning the system, due to complex calculation structure and wide ranges for tuning parameters. This paper describes and exam...

In this study, we reproduce the results from an existing paper on PID tuning using extremum seeking (ES) methods. In addition to analyzing performance with respect to existing tuning methods, we investigate the ES algorithm parameters and how their values impact stability and convergence speed. To demonstrate the efficacy of ES on tuning classical controllers, we apply the algorithm to a simple...