We consider the problem of prediction of stationary time series, using the architecture known as mixtures of experts (MEM). Here we suggest a mixture which blends several autoregressive models. This study focuses on some theoretical foundations of the prediction problem in this context. More precisely, it is demonstrated that this model is a universal approximator, with respect to learning the ...

The direct adaptive dynamic regulation of unknown nonlinear multi variable systems is investigated in this chapter in order to address the problem of controlling non-Brunovsky and non-square systems with control inputs less than the number of states. The proposed neuro-fuzzy model acts as a universal approximator. While with the careful selection of a Lyapunov-like function, the authors prove t...

We consider the adaptive tracking problem for a chain of integrators, where the uncertainty is static and functional. The uncertainty is specified by L2=Ly or weighted L2=Ly norm bounds. We analyse a standard Lyapunovbased adaptive design which utilises a function approximator to induce a parametric uncertainty, on which the adaptive design is completed. Performance is measured by a modified LQ...

The single-layer perceptron, introduced by Rosenblatt in 1958, is one of the earliest and simplest neural network models. However, it incapable classifying linearly inseparable patterns. A new era research started 1986, when backpropagation (BP) algorithm was rediscovered for training multilayer perceptron (MLP) model. An MLP with a large number hidden nodes can function as universal approximat...

Abstract The universal approximation property of various machine learning models is currently only understood on a case-by-case basis, limiting the rapid development new theoretically justified neural network architectures and blurring our understanding current models’ potential. This paper works towards overcoming these challenges by presenting characterization, representation, construction me...

A bstract In this work, our prime objective is to study the phenomena of quantum chaos and complexity in machine learning dynamics Quantum Neural Network (QNN). Parameterized Circuits (PQCs) hybrid quantum-classical framework introduced as a universal function approximator perform optimization with Stochastic Gradient Descent (SGD). We employ statistical differential geometric approach theory Q...

In established network architectures, shortcut connections are often used to take the outputs of earlier layers as additional inputs later layers. Despite extraordinary effectiveness shortcuts, there remain open questions on mechanism and characteristics. For example, why shortcuts powerful? Why do generalize well? this article, we investigate expressivity generalizability a novel sparse topolo...

The distributional reinforcement learning (RL) approach advocates for representing the complete probability distribution of random return instead only modelling its expectation. A RL algorithm may be characterised by two main components, namely representation together with parameterisation and metric defining loss. present research work considers unconstrained monotonic neural network (UMNN) ar...

Winding/unwinding system control is a very important issue to web handling machines. In this paper, a novel adaptive H∞ control strategy is developed for winding process control. A gain scheduling scheme is proposed based on a neural fuzzy approximator to improve the transient response and enhance tension control; the controller’s convergence and adaptive capability can be further improved by a...