In this paper, a new adaptive fuzzy reasoning method using compensatory fuzzy operators is proposed to make a fuzzy logic system more adaptive and more effective. Such a compensatory fuzzy logic system is proved to be a universal approximator. The compensatory neural fuzzy networks built by both control-oriented fuzzy neurons and decision-oriented fuzzy neurons cannot only adaptively adjust fuz...

Although vast research works have been paid (throughout some 20 years back) regarding formal synthesis of an ANN it is somehow still open issue. This paper does not consider the mentioned formal synthesis aspects but intends to introduce an original engineering approach offering some advantages whenever training and designing of artificial neurel networks are under consideration. In that sense ...

In this work, a new method is proposed for hand tracking based on a density approximation and optimization method. Considering tracking as a classification problem, we train an approxiator to recognize hands from its background. This procedure is done by extracting feature vector of every pixel in the first frame and then building an approximator to construct a virtual optimized surface of pixe...

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 two of its 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 prope...

A new autopilot design for bank-to-turn (BTT) missiles is presented. In the design of autopilot, a ridge Gaussian neural network with local learning capability and fewer tuning parameters than Gaussian neural networks is proposed to model the controlled nonlinear systems. We prove that the proposed ridge Gaussian neural network, which can be a universal approximator, equals the expansions of ro...

This paper investigates function approximation on discrete input spaces by both neural networks and neural-fuzzy systems. Rather than use existing neural networks for function approximation on continuous input spaces, this paper proposes, based on a hierarchical systematic perspective, four simplified approximation schemes: simplified neural networks, extended simplified neural networks, simple...

The research on robust principal component analysis (RPCA) has been attracting much attention recently. The original RPCA model assumes sparse noise, and use the L1-norm to characterize the error term. In practice, however, the noise is much more complex and it is not appropriate to simply use a certain Lp-norm for noise modeling. We propose a generative RPCA model under the Bayesian framework ...

This paper presents a method that combines Mutual Information and k-Nearest Neighbors approximator for time series prediction. Mutual Information is used for input selection. K-Nearest Neighbors approximator is used to improve the input selection and to provide a simple but accurate prediction method. Due to its simplicity the method is repeated to build a large number of models that are used f...

Value functions are a core component of reinforcement learning systems. The main idea is to to construct a single function approximator V (s; θ) that estimates the long-term reward from any state s, using parameters θ. In this paper we introduce universal value function approximators (UVFAs) V (s, g; θ) that generalise not just over states s but also over goals g. We develop an efficient techni...

The Random Neural Network (RNN) is a recurrent neural network model inspired by the spiking behaviour of biological neuronal networks. Contrary to most Artificial Neural Networks (ANN) models, neurons in RNN interact by probabilistically exchanging excitatory and inhibitory spiking signals. The model is described by analytical equations, has a low complexity supervised learning algorithm and is...