The aim, and main contribution, of this paper is to propose a fine-tuned fast approximator, based on neural networks, that uses aggregated traction system information as inputs and outputs. This approximator can be used as an investment planning constraint in the optimization. It considers that there is a limit on the intensity of the train traffic, depending on the strength of the power system...

In this article, a novel combined i-vector and an Extreme Learning Machine (ELM) is proposed for speaker identification. The ELM chosen because it fast to train has universal approximator property. Four combinations of features based on Mel Frequency Cepstral Coefficient Power Normalized are used. Besides, seven fusion methods exploited. system evaluated with three different databases, namely: ...

Recently an incremental algorithm referred to as incremental extreme learning machine (I-ELM) was proposed by Huang et al. [G.-B. Huang, L. Chen, C.-K. Siew, Universal approximation using incremental constructive feedforward networks with random hidden nodes, IEEE Trans. Neural Networks 17(4) (2006) 879–892], which randomly generates hidden nodes and then analytically determines the output weig...

In this paper, a type of compensation-based recurrent fuzzy neural network (CRFNN) for identifying dynamic systems is proposed. The proposed CRFNN uses a compensation-based fuzzy reasoning method, and has feedback connections added in the rule layer of the CRFNN. The compensation-based fuzzy reasoning method can make the fuzzy logic system more adaptive and effective, and the additional feedbac...

Convergence for iterative reinforcement learning algorithms like TD(O) depends on the sampling strategy for the transitions. However, in practical applications it is convenient to take transition data from arbitrary sources without losing convergence. In this paper we investigate the problem of repeated synchronous updates based on a fixed set of transitions. Our main theorem yields sufficient ...

We introduce two new models which are obtained through the modification of the well known methods MLP and cascade correlation. These two methods differ fundamentally as they employ learning techniques and produce network architectures that are not directly comparable. We extended the MLP architecture, and reduced the constructive method to obtain very comparable network architectures. The great...

This paper presents a special hierarchical fuzzy system where the outputs of the previous layer are not used in the IF-parts, but used only in the THEN-parts of the fuzzy rules of the current layer. The proposed scheme can be shown to be a universal approximator to any continuous function on a compact set if complete fuzzy sets are used in the IF-parts of the fuzzy rules with singleton fuzzi5er...

In this paper, a type of fuzzy system structure is applied to heuristic dynamic programming (HDP) algorithm to solve nonlinear discrete-time Hamilton–Jacobi–Bellman (DT-HJB) problems. The fuzzy system here is adopted as a 0-order T–S fuzzy system using triangle membership functions (MFs). The convergence of HDP and approximability of the multivariate 0-order T–S fuzzy system is analyzed in this...

Incorporating prior knowledge of a particular task into the architecture of a learning algorithm can greatly improve generalization performance. We study here a case where we know that the function to be learned is non-decreasing in its two arguments and convex in one of them. For this purpose we propose a class of functions similar to multi-layer neural networks but (1) that has those properti...