Journal•ISSN: 1370-4621

# Neural Processing Letters

Springer Science+Business Media

About: Neural Processing Letters is an academic journal published by Springer Science+Business Media. The journal publishes majorly in the area(s): Artificial neural network & Computer science. It has an ISSN identifier of 1370-4621. Over the lifetime, 2782 publications have been published receiving 45490 citations.

Topics: Artificial neural network, Computer science, Artificial intelligence, Computational intelligence, Convolutional neural network

##### Papers published on a yearly basis

##### Papers

More filters

••

TL;DR: A least squares version for support vector machine (SVM) classifiers that follows from solving a set of linear equations, instead of quadratic programming for classical SVM's.

Abstract: In this letter we discuss a least squares version for support vector machine (SVM) classifiers. Due to equality type constraints in the formulation, the solution follows from solving a set of linear equations, instead of quadratic programming for classical SVM‘s. The approach is illustrated on a two-spiral benchmark classification problem.

8,811 citations

••

TL;DR: In this study, differential evolution has been analyzed as a candidate global optimization method for feed-forward neural networks and seems not to provide any distinct advantage in terms of learning rate or solution quality.

Abstract: An evolutionary optimization method over continuous search spaces, differential evolution, has recently been successfully applied to real world and artificial optimization problems and proposed also for neural network training However, differential evolution has not been comprehensively studied in the context of training neural network weights, ie, how useful is differential evolution in finding the global optimum for expense of convergence speed In this study, differential evolution has been analyzed as a candidate global optimization method for feed-forward neural networks In comparison to gradient based methods, differential evolution seems not to provide any distinct advantage in terms of learning rate or solution quality Differential evolution can rather be used in validation of reached optima and in the development of regularization terms and non-conventional transfer functions that do not necessarily provide gradient information

599 citations

••

TL;DR: A novel self-organizing network which is generated by a growth process where both the neighborhood range used to co-adapt units in the vicinity of the winning unit and the adaptation strength are constant during the growth phase.

Abstract: We present a novel self-organizing network which is generated by a growth process. The application range of the model is the same as for Kohonen’s feature map: generation of topology-preserving and dimensionality-reducing mappings, e.g., for the purpose of data visualization. The network structure is a rectangular grid which, however, increases its size during self-organization. By inserting complete rows or columns of units the grid may adapt its height/width ratio to the given pattern distribution. Both the neighborhood range used to co-adapt units in the vicinity of the winning unit and the adaptation strength are constant during the growth phase. This makes it possible to let the network grow until an application-specific performance criterion is fulfilled or until a desired network size is reached. A final approximation phase with decaying adaptation strength finetunes the network.

341 citations

••

TL;DR: It is shown that the fast fixed-point algorithm is closely connected to maximum likelihood estimation as well, and modifications of the algorithm maximize the likelihood without constraints.

Abstract: The author previously introduced a fast fixed-point algorithm for independent component analysis. The algorithm was derived from objective functions motivated by projection pursuit. In this paper, it is shown that the algorithm is closely connected to maximum likelihood estimation as well. The basic fixed-point algorithm maximizes the likelihood under the constraint of decorrelation, if the score function is used as the nonlinearity. Modifications of the algorithm maximize the likelihood without constraints.

300 citations

••

TL;DR: In this paper, a greedy algorithm for learning a Gaussian mixture is proposed, which uses a combination of global and local search each time a new component is added to the mixture and achieves solutions superior to EM with k components in terms of the likelihood of a test set.

Abstract: Learning a Gaussian mixture with a local algorithm like EM can be difficult because (i) the true number of mixing components is usually unknown, (ii) there is no generally accepted method for parameter initialization, and (iii) the algorithm can get trapped in one of the many local maxima of the likelihood function. In this paper we propose a greedy algorithm for learning a Gaussian mixture which tries to overcome these limitations. In particular, starting with a single component and adding components sequentially until a maximum number k, the algorithm is capable of achieving solutions superior to EM with k components in terms of the likelihood of a test set. The algorithm is based on recent theoretical results on incremental mixture density estimation, and uses a combination of global and local search each time a new component is added to the mixture.

295 citations