This paper describes, and discusses Bayesian Neural Network (BNN). The paper showcases a few different applications of them for classification and regression problems. BNNs are comprised of a Probabilistic Model and a Neural Network. The intent of such a design is to combine the strengths of Neural Networks and Stochastic modeling. Neural Networks exhibit universal continuous function approxima...

This paper explores the problem of finding a real–time optimal trajectory for unmanned air vehicles (UAV) in order to minimize their probability of detection by opponent multiple radar detection systems. The problem is handled using the Nonlinear Trajectory Generation (NTG) method developed by Milam et al. The paper presents a formulation of the trajectory generation task as an optimal control ...

Many studies on modeling of fuzzy inference systems have been made. The issue of these studies is to construct automatically fuzzy inference systems with interpretability and accuracy from learning data based on metaheuristic methods. Since accuracy and interpretability are contradicting issues, there are some disadvantages for self-tuning method by metaheuristic methods. Obvious drawbacks of t...

The design of a complete expansion that allows for compact representation of certain relevant classes of signals is a central problem in signal processing applications. Achieving such a representation means knowing the signal features for the purpose of denoising, classification, interpolation and forecasting. Multilayer Neural Networks are relatively a new class of techniques that are mathemat...

The situation and trends in the application of fuzzy logic to control multi-input/multi-output (MIMO) systems are analyzed. The basic steps in designing a control system are considered. Fuzzy control applications are either knowledge-based or model-based. In model-based approaches, the first step is process modeling: Usually, interpolation and universal approximation are the two main features t...

An Artificial Neural Network(ANN) is a well known universal approximator to model smooth and continuous functions. ANNs operate in two stages: learning and generalization. Learning of a neural network is to approximate the behavior of the training data while generalization is the ability to predict well beyond the training data. In order to have a good learning and generalization ability , a go...

This paper introduces a heuristic methodology for designing multilayer feedforward neural networks to be used in modeling nonlinear functions in engineering mechanics applications. It is well recognized that a perfect way to decide an appropriate architecture and assign initial values to start neural network training has yet to be established. This might be because such a challenging issue can ...

This paper reports a novel deep architecture referred to as Maxout network In Network (MIN), which can enhance model discriminability and facilitate the process of information abstraction within the receptive field. The proposed network adopts the framework of the recently developed Network In Network structure, which slides a universal approximator, multilayer perceptron (MLP) with rectifier u...

We develop a new nonparametric method to reconstruct the Equation of State (EoS) Neutron Star with multimessenger data. As an universal function approximator, Feed-Forward Neural Network (FFNN) one hidden layer and sigmoidal activation can approximately fit any continuous function. Thus we are able implement FFNN representation EoSs. This is validated by its capabilities fitting theoretical EoS...